Key Takeaways

• 6G’s success hinges on solving RF hardware bottlenecks before standardization completes. The race to design next-gen radio frequency components—like terahertz transceivers and digital twins—is outpacing 3GPP’s timeline, creating a strategic divide between early movers and followers The Hidden 6G Bottleneck: RF Hardware Design I… 6G in Dalian: What the Latest 3GPP Meetings Re….
• 3GPP’s latest meetings in Dalian revealed three critical 6G radio challenges: terahertz beamforming, AI-native PHY layers, and cross-layer optimization, all requiring hardware prototypes before 2026 6G in Dalian: What the Latest 3GPP Meetings Re….
• RF digital twins are emerging as a prerequisite for 5G-Advanced and 6G, enabling predictive simulation of interference and propagation—yet no vendor has commercialized them at scale RF Digital Twins: Why 5G-Advanced and 6G Need ….
• The industry’s focus on 6G PHY evolution is shifting from theoretical gains to practical constraints: power efficiency, thermal management, and supply chain resilience for millimeter-wave and terahertz chips Evaluating 6G PHY Evolution: What the Industry….
• Amazon’s $886M Globalstar acquisition accelerates its D2D ambitions by leveraging satellite spectrum, but regulatory hurdles in the U.S. and EU could delay deployment Amazon’s Globalstar deal gives Amazon Leo a fa….
• LLMs’ deductive reasoning gaps persist even with tool augmentation, as benchmarks show they struggle to verify assumptions or flag missing knowledge—limiting their use in high-stakes domains like healthcare Clueing up LLMs with Tool-Augmented Deductive … Do small language models know what they don't ….

• Africa’s mobile internet gap widens as AI and hardware costs diverge. GSMA’s 2030 roadmap targets 1B new connections, but smartphone component inflation and AI-driven demand risk leaving 3B offline unless supply chains adapt GSMA warns of emerging global AI divide as thr… GSMA and PDAA Unveil Roadmap to Close Africa&#….
• Rwanda’s digital reforms could bridge 1M+ connections, but success depends on renewable energy access—a bottleneck in Asia Pacific where mobile operators face net-zero transition costs Digital Reforms Could Connect Over 1 Million M… GSMA calls for greater renewable energy access….
• Adversarial trading contagion in multi-agent systems reveals systemic risks: AI-driven market-making agents amplify liquidity shocks when exposed to coordinated signals Contagion on the Trading Floor: How Adversaria….
• LLM-based penetration testing agents introduce new security threats, including adversarial prompt injection and model inversion attacks, requiring verifiable "action cards" for human oversight Toward Secure AI-Powered Penetration Testing A….
• Physics-grounded robotics (e.g., off-road traversability, tactile-vision-language models) is advancing faster than AI alignment research, with benchmarks like PIVOT and ForeTac-VLA achieving 92%+ accuracy in unstructured environments ForeTac-VLA: A Forecasting-Based Tactile-Visio… PIVOT: Physically Informed Vision-Language Off….

---

Executive Summary

Today’s tech and economics landscape is defined by hardware-led races in 6G and structural divides in digital access. The 3GPP’s Dalian meetings laid bare the tension between theoretical 6G standardization and practical RF bottlenecks, particularly in terahertz transceivers and AI-native PHY layers 6G in Dalian: What the Latest 3GPP Meetings Re…. Meanwhile, Amazon’s Globalstar deal signals a pivot toward direct-to-device (D2D) connectivity, but regulatory and supply chain hurdles loom Amazon’s Globalstar deal gives Amazon Leo a fa…. On the AI front, deductive reasoning gaps in LLMs—even with tool augmentation—highlight persistent limitations in domains like healthcare Clueing up LLMs with Tool-Augmented Deductive … Do small language models know what they don't …, while adversarial risks in autonomous agents (e.g., trading systems, penetration testers) demand new guardrails Toward Secure AI-Powered Penetration Testing A… Contagion on the Trading Floor: How Adversaria…. In economics, GSMA’s 2030 Africa roadmap contrasts with soaring smartphone component costs, which threaten to widen the digital divide unless renewable energy and local manufacturing improve GSMA and PDAA Unveil Roadmap to Close Africa&#… GSMA warns of emerging global AI divide as thr…. Finally, physics-grounded robotics (e.g., off-road navigation, tactile-vision models) is outpacing AI alignment research, with benchmarks achieving near-human performance in unstructured tasks ForeTac-VLA: A Forecasting-Based Tactile-Visio… PIVOT: Physically Informed Vision-Language Off….

---

6G Hardware Wars: The RF Bottleneck Before Standardization

The 6G timeline is collapsing under the weight of RF hardware constraints, with vendors racing to prototype terahertz transceivers and digital twins before 3GPP finalizes specifications. Meetings in Dalian revealed three urgent priorities: terahertz beamforming for ultra-high-bandwidth links, AI-native PHY layers to compensate for signal degradation, and cross-layer optimization to mitigate thermal and power inefficiencies 6G in Dalian: What the Latest 3GPP Meetings Re…. Unlike 5G, where software-defined radios (SDRs) bridged the gap, 6G’s millimeter-wave and terahertz frequencies require custom silicon—creating a strategic advantage for early movers like Samsung, Huawei, and Ericsson The Hidden 6G Bottleneck: RF Hardware Design I…. The absence of commercial RF digital twins further exacerbates the problem, as predictive simulation tools are still in R&D phases RF Digital Twins: Why 5G-Advanced and 6G Need …. Industry focus has shifted from theoretical data rates to practical constraints: supply chain resilience for gallium nitride (GaN) transistors, and the ability to integrate AI accelerators into baseband processors Evaluating 6G PHY Evolution: What the Industry….

---

Amazon’s D2D Gambit: Globalstar as a Bridge to Satellite-Direct Connectivity

Amazon’s $886M acquisition of Globalstar accelerates its Amazon Leo project by securing low-Earth orbit (LEO) spectrum for direct-to-device (D2D) communications, bypassing traditional cellular gateways Amazon’s Globalstar deal gives Amazon Leo a fa…. The deal aligns with 3GPP’s Rel-18 work on non-terrestrial networks (NTN), but regulatory hurdles—particularly in the U.S. (where Globalstar’s spectrum licenses are contested) and EU (where satellite D2D faces spectrum allocation delays)—could postpone commercial launches 6G in Dalian: What the Latest 3GPP Meetings Re…. Unlike Starlink’s broadband focus, Amazon Leo targets ultra-low-latency messaging and IoT, positioning it as a competitor to 5G D2D and CBRS-based solutions. The acquisition also strengthens Amazon’s satellite-ground integration capabilities, though it remains unclear whether the company will prioritize standalone D2D or hybrid 5G-satellite networks Amazon’s Globalstar deal gives Amazon Leo a fa….

---

The AI Divide: Why 3 Billion Offline Users Face Higher Costs Than Ever

GSMA’s warnings about a global AI divide take on new urgency as smartphone component costs soar, particularly for AI accelerators and 5G modems GSMA warns of emerging global AI divide as thr…. While Africa’s 2030 roadmap aims to connect 1 billion people, the $100+ price premium for AI-capable devices in emerging markets risks exacerbating the digital gap GSMA and PDAA Unveil Roadmap to Close Africa&#…. The issue extends beyond hardware: renewable energy access—critical for mobile towers in rural areas—remains a bottleneck in Asia Pacific, where operators face net-zero transition costs of $200B+ by 2030 GSMA calls for greater renewable energy access…. Rwanda’s digital reforms offer a potential model, with LLM-assisted connectivity planning projected to add 1 million users by 2025 Digital Reforms Could Connect Over 1 Million M…. However, the broader challenge is supply chain localization: without reductions in semiconductor and battery costs, the GSMA’s 2030 targets may hinge on subsidized devices rather than organic adoption.

---

Adversarial AI in Trading: How Multi-Agent Systems Amplify Market Contagion

New research on multi-agent trading systems reveals how adversarial signals can trigger contagious liquidity shocks, even in concentrated liquidity markets Contagion on the Trading Floor: How Adversaria…. Unlike traditional high-frequency trading (HFT), AI-driven market-making agents exhibit nonlinear feedback loops: a single adversarial agent can manipulate order books, prompting cascading liquidity withdrawal across agents SAiFE-gym: Model-based Environments for Automa…. The SAiFE-gym benchmark demonstrates that reinforcement learning-based agents are particularly vulnerable when exposed to coordinated manipulation, with some systems failing to recover within 100 trading cycles SAiFE-gym: Model-based Environments for Automa…. While deep learning credit risk models improve early warning systems Design of a Deep Learning Credit Risk Early Wa…, the lack of standardized adversarial testing means most exchanges remain blind to multi-agent contagion risks. Regulators are beginning to explore dynamic liquidity thresholds, but the absence of a unified framework leaves gaps in systemic resilience Contagion on the Trading Floor: How Adversaria….

---

Physics-Grounded Robotics Outpaces AI Alignment Research

Advances in physics-aware robotics are achieving near-human performance in unstructured environments, yet AI alignment research lags behind. Models like ForeTac-VLA—which combines tactile, vision, and language inputs—reach 92% accuracy in contact-rich manipulation tasks, while PIVOT enables off-road traversability with <5% error rates in GPS-denied zones ForeTac-VLA: A Forecasting-Based Tactile-Visio… PIVOT: Physically Informed Vision-Language Off…. These systems rely on hybrid neural-symbolic reasoning, integrating Newtonian physics constraints into LLMs, unlike most AI agents that treat perception as purely data-driven. The gap is stark: while robotics benchmarks now include real-world physics tests, AI safety research remains focused on text-based adversarial attacks Toward Secure AI-Powered Penetration Testing A…. This divergence risks decoupling robotic autonomy from general AI safety, as physics-grounded systems may develop unintended emergent behaviors in dynamic environments ForeTac-VLA: A Forecasting-Based Tactile-Visio….

Babak's Daily Briefing

Monday, September 21, 2026

Sources: 20 | Total Articles: 92

• 1.The Hidden 6G Bottleneck: RF Hardware Design Is Becoming a Strategic Race

  As 5G-Advanced matures and 6G research moves closer to implementation, the wireless industry faces a deeper challenge than spectrum, standards or AI-native network architecture. Future wireless systems will depend on whether the industry can design, validate and manufacture increasingly complex RF modules fast enough.

• 2.6G in Dalian: What the Latest 3GPP Meetings Reveal About the Future Radio and Network

  The 6G physical layer is starting to converge. The protocol stack is being simplified in meaningful places. But the most consequential architecture decisions are now moving toward the June plenary in Singapore.

• 3.RF Digital Twins: Why 5G-Advanced and 6G Need Predictive Simulation

  RF Digital Twins: Why 5G-Advanced and 6G Need Predictive Simulation As wireless systems become more tightly coupled across…

• 4.Evaluating 6G PHY Evolution: What the Industry Is Really Trying to Solve

  Summary available at source link.

• 5.Amazon’s Globalstar deal gives Amazon Leo a faster path into D2D

  Amazon’s planned acquisition of Globalstar is about far more than satellites. It gives Amazon Leo a faster path into direct-to-device connectivity, combining spectrum, operational assets, and Apple-facing service continuity in a move that could reshape the hybrid terrestrial-NTN landscape.

• 1.A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents

  LLM-based GUI agents increasingly act on behalf of users in digital environments that were designed with human users in mind. These graphical user interfaces were designed to support, but also deliberately steer, the behaviour and decisions of users. While behavioural biases in the textual outputs of LLMs are well-documented, far less is known about how such influence operates when models act as agents that perceive interfaces and execute decisions---and, in particular, whether the reasoning capabilities increasingly built into these agents make them more robust to it. Drawing on Dual-Process Theory, we empirically investigate whether LLM-based GUI agents are susceptible to automatic (Type 1) and reflective (Type 2) digital nudges, and how their reasoning configuration moderates this susceptibility. In a randomized online shopping experim...

• 2.Clueing up LLMs with Tool-Augmented Deductive Reasoning

  Despite recent advances in large language models (LLMs), performing logically consistent deductive reasoning over extended interactions remains challenging. Tasks that require integrating evidence across multiple reasoning steps, maintaining consistency with prior inferences, and updating beliefs under new constraints can surface limitations in current models while providing a useful testbed for evaluating reasoning enhancements. In this paper, we implement a text-based, multi-agent version of the classic board game Clue as an environment to evaluate multi-step, agentic deductive reasoning. In this setting, agents must infer hidden information from a sequence of observations, maintain consistency across turns, and reason over an evolving set of logical constraints. We instantiate six LLM-based agents (GPT-4o-mini and Gemini-2.5-Flash) as ...

• 3.The Verifiable Action Card: Trustworthy Human-in-the-Loop Control for Secure Autonomous Agents

  Agentic browsers can execute security-sensitive actions under a user's authenticated session, making indirect prompt injection and deceptive confirmation interfaces a direct threat to action integrity. Existing human-in-the-loop (HITL) safeguards are insufficient when the approval prompt itself can be influenced by untrusted page content or model-generated text. We present the \emph{Verifiable Action Card} (VAC), an architectural defence that reconstructs approval information from the ground-truth pending browser action and trusted intent provenance, renders it out-of-band in the trusted browser chrome, and binds approval to the exact action re-verified at dispatch. VAC combines provenance fencing, a ground-truth action descriptor, default-deny confirmation, provenance-aware risk gating, and execution binding. We implement VAC in a comple...

• 4.Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives

  LLM-powered autonomous agents are transforming the penetration testing space with dynamic, multi-step offensive security workflows that require minimal supervision by humans. These agents leverage sophisticated reasoning abilities and external security tools to independently carry out reconnaissance, identify vulnerabilities, devise exploitation plans, and perform post-exploitation operations. But the ability to have persistent memory, to take actions in the real world, and to do long-horizon reasoning raises qualitatively different security concerns than traditional chat-based LLM systems. Existing guardrail mechanisms for conversational AI may not be sufficient to secure autonomous AI pentesting agents accordingly. To address these issues, we carry out a comprehensive security analysis on autonomous AI-penetration testing agents. We sys...

• 5.Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents

  Autonomous agents powered by large language models (LLMs) continuously accumulate experience through interaction, creating an opportunity to improve future behavior through self-evolution. A fundamental challenge is how to transform abundant, task-specific interaction experience into reusable model competence without sacrificing the ability to adapt rapidly to newly observed evidence. Explicit textual states, such as skills and agent harnesses, provide fast, human-readable and editable adaptation, but incur persistent dependence on external context; parametric policies provide compact and reusable competence, but are substantially slower to update. We present \textit{Experience Funnel}, a self-evolving framework that couples fast state adaptation with slow policy consolidation in an alternating loop. Interaction trajectories are first dis...

• 1.Do small language models know what they don't know?

  arXiv:2609.20824v1 Announce Type: new Abstract: We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small Language Models (SLMs) with fewer than 3 billion parameters, running entirely on consumer hardware. We evaluate seven distinct approaches, including token-level entropy early stopping, semantic entropy estimation, and uncertainty-aware routing to larger expert models, across 7 model pairs and 5 standard NLU benchmarks. Our key finding is that token-level entropy is effectively blind in SLMs: in 91% of dataset-model combinations, mean token entropy is near zero regardless of answer correctness, rendering token-based confidence signals unusable at this scale. We demonstrate that semantic entropy, computed by generating multiple samples, clustering answers by meaning, and measuring distributio...

• 2.HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction

  arXiv:2609.20825v1 Announce Type: new Abstract: Clinical predictive models often rely on structured Electronic Health Record data, such as time-series and procedure codes. While recent approaches have begun leveraging unstructured clinical notes, they typically encode them as flat sequences, which may lose explicit relational and temporal structure present in clinical narratives. In response, we propose HERMES, a graph-based framework that operates exclusively on clinical text while preserving clinical relationships. This approach builds on two key ideas. First, personalized Knowledge Graphs (KGs) are constructed through Large-Language-Model-guided extraction from clinical notes with Contrastive Logic Modeling that explicitly captures temporal dynamics and treatment failures and changes in outcomes. Second, a Graph Attention Network synt...

• 3.TALON: A Temporally Aware Longitudinal Framework for Radiology Report Generation

  arXiv:2609.20826v1 Announce Type: new Abstract: Current radiology report generation (RRG) models usually produce descriptive reports based on a single examination or only the most recent prior examination, limiting their ability to perform accurate and meaningful longitudinal comparisons and detect subtle interval changes. Although recent approaches have begun to incorporate multiple prior examinations, they usually aggregate a fixed-length history without explicitly modeling the role-dependent relevance of each prior examination before fusion. To address this, we propose TALON, a Temporally Aware LONgitudinal RRG framework that adaptively integrates variable-length patient histories. The underlying Dual-Channel Temporal Fusion Module (DCTFM) compares the current examination with each prior examination through complementary similarity an...

• 4.From Discharge Notes to Patient Understanding: Persona-Grounded, Open-Ended Simulation of LLMs as Discharge Educators

  arXiv:2609.20827v1 Announce Type: new Abstract: Hospital discharge education is an interactive teaching task: a clinician adapts a discharge plan to a patient's literacy, recall, and personality. Existing LLM evaluations target static or artifact-generation tasks and do not measure patient understanding under open-ended dialogue. We introduce DischargeBench, a persona-grounded simulation in which a candidate LLM educator conducts a multi-turn session with a Virtual Patient, while an Education Monitor Agent regulates patient realism without modifying the educator, protecting the evaluation signal. We curate MIMIC-IV-Ext-DischargeBench, 477 cases over 24 ICD chapters with persona axes (personality, education level, health literacy, past-medical-history recall) for stratified analysis. Each simulation is scored on four axes -- Conversation ...

• 5.Beyond WER: Entity and Disfluency Recall in Accented Conversational ASR

  arXiv:2609.20828v1 Announce Type: new Abstract: ASR systems optimised for Word Error Rate (WER) often miss named entities and filled pauses in accented conversational English, both critical for language-learning feedback. We present a three-stage pipeline for speakers from India, Indonesia, and Latin America: (1) heuristic SQL filters curating entity-rich training data at 2.8x the entity density of random sampling, (2) regional LoRA adapters fine-tuned on Qwen2.5-Omni-3B producing both verbatim and corrected transcripts in a single forward pass, and (3) a six-category error taxonomy validated by an LLM-based judge (83.8% agreement, 210 human-labelled samples). The pipeline achieves 80-85% entity recall (up from 53-55%), 76-86% filler recall (up from <5%), and 6-10% WER across 6k test utterances, outperforming Whisper and a commercial ASR...

• 1.Sparse Priors for Efficient Distribution Learning

  arXiv:2609.20883v1 Announce Type: new Abstract: Despite the widespread use and success of generative AI techniques today, theoretical guarantees on learning a distribution supported in $d$ dimensions from $n$ samples degrade as $O(n^{-1/\Theta(d)})$, though shown to be minimax optimal. We hypothesize that present bounds are too pessimistic because smoothness assumptions are not enough to capture the structure of distributions that often appear in real applications. Consequently, we introduce the class of sparse priors and define the "Sparse Dimension" as a measure of sparsity of a prior over the space of all distributions. We show that distribution learning under a $k$-sparse prior achieves a Bayesian risk lower bound of $\Omega(\sqrt{k/n})$ under common distance metrics, and show a matching (up to logarithmic terms asymptotically in $n,k...

• 2.BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

  arXiv:2609.20886v1 Announce Type: new Abstract: Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau. In traditional BI workflows, users need to prepare data by (1) identifying relevant tables, (2) performing data transformations, and (3) building join relationships, before they can (4) answer their business questions. These steps can be complex and time-consuming, making BI challenging. Given the strong capabilities of large language models (LLMs) in working with data, we study their ability to answer BI questions end-to-end, without requiring users to manually perform the tedious preparation steps. To do this, we harvest a large collection of real-world BI projects from public sources, and manually extract pairs of (questions, ground-tru...

• 3.Elastic Threshold Attention: Learned Contextual Sparsity for Long-Context Decoding

  arXiv:2609.20888v1 Announce Type: new Abstract: Massive KV caches can cause severe memory-bandwidth bottlenecks during long-context decoding. Sparse attention methods mitigate this via selective loading, but that comes at a cost: rigid heuristics drop necessary context, leading to quality degradation. We introduce \textbf{Elastic Threshold Attention (ETA)}, an end-to-end trainable architecture that achieves hardware-accelerated decoding speed without sacrificing dense model quality. ETA predicts dynamic, contextual thresholds directly from query representations, allowing the model to allocate dense-like context to difficult retrieval or reasoning steps while pruning routine tokens. To learn this policy from scratch without representation collapse, ETA \emph{multiplicatively suppresses} sub-threshold logits toward zero during training rath...

• 4.Bio-MF: Low-Latency and High-Fidelity EEG-to-fNIRS Cross-Modal Generation for Hybrid Motor-Imagery Brain--Computer Interfaces

  arXiv:2609.20904v1 Announce Type: new Abstract: Hybrid motor-imagery brain-computer interfaces (MI-BCIs) combining EEG and fNIRS can outperform EEG-only systems by exploiting complementary electrophysiological and hemodynamic information. To obtain such hybrid information when paired EEG-fNIRS acquisition is unavailable or inconvenient, recent studies have focused on EEG-to-fNIRS cross-modal generation. However, existing methods still suffer from slow generation and often require pretraining, limiting their use in real-time MI-BCI scenarios. Although one-step generative models offer an attractive route to low-latency synthesis, removing the iterative refinement process can reduce generation fidelity and introduce non-physiological artifacts. To address these problems, this paper proposes Bio-MF, a latent-free one-step MeanFlow framework f...

• 5.Continuous Delayed-Memory Stochastic Gradient Descent and Continuous-Time Reinforcement Learning from History of Astrophysical Time Series Studies

  arXiv:2609.20906v1 Announce Type: new Abstract: Quasars are luminous objects in the universe that exhibit stochastic brightness variations encoding information about the supermassive black holes powering them, and modeling these variations from ground-based survey data time series, known as light curves, is a statistical challenge. This paper reviews how stochastic differential equations (SDEs) have been adapted with neural network parameterizations to overcome this challenge in history. We create the Continuous-Delayed-Memory Stochastic Gradient Descent which depend on the past state of the discrete iteration process. We performed the simulation on some 2-dimensional landscape and observed some wider-exploration and more precise convergent behavior compared to Vanilla SGD by adjusting hyperparameters. Besides, we proposed a reinforcement...

• 1.WM-VS: Progress-Aligned World Models for Closed-Loop Visual Servoing

  arXiv:2609.20892v1 Announce Type: new Abstract: Closed-loop visual servoing requires predictions that indicate whether an action reduces task error, not only whether the action is plausible. We call this gap the prediction-control mismatch and introduce WM-VS, a target-centric progress-aligned world-model framework for closed-loop visual servoing. Offline target-region DINOv2 correspondences define a signed four-dimensional servo coordinate for translation, scale, and in-plane rotation. Stage 1 aligns action-conditioned latent transitions with this coordinate; Stage 2 freezes the world model and trains a reactive joint-velocity policy with action imitation, consequence supervision, and short imagined rollouts that favor error contraction. Deployment is RGB-only and reactive, without online trajectory optimization. On a real 7-DoF eye-to-h...

• 2.AeRove: A Compact Bimodal Aerial-Terrestrial Drone with Rapid Bistable Reconfiguration for Close-Range Pipeline Inspection

  arXiv:2609.20965v1 Announce Type: new Abstract: Close-proximity pipeline inspection is challenging for standard drones due to high hovering power consumption, airflow sensitivity, and propeller wash interference with gas sensing. To address this, we present AeRove, a compact bimodal aerial-terrestrial robot. AeRove uses its propeller guards as wheels to roll along pipes and employs a spring-loaded bistable mechanism to reconfigure between ground and flight modes in 200 ms without continuous actuator power to maintain either state. The converging propeller-guard geometry also improves measured thrust efficiency. By reserving flight for obstacle hopping and using ground rolling for continuous traversal, current draw is reduced 14x compared to continuous flight (0.7 A vs. 10 A), extending estimated travel distance from 144 m to 2057 m. Auton...

• 3.Shake to Learn: Dynamic Interrogation of Hidden Object Physics for Robotic Manipulation with Physical Reservoir Computing

  arXiv:2609.20970v1 Announce Type: new Abstract: Many physical properties relevant to robotic manipulation are hidden from vision. A sealed object, for example, may reveal little about its center of mass (COM) or internal contents until it is lifted, shaken, or otherwise dynamically perturbed. This study shows that such interactions can enable a new modality of robotic perception and learning, in which interaction-induced dynamic responses are used to infer object physics that is inaccessible to conventional sensing. We implement this idea using an origami-inspired soft robotic arm that functions as a physical reservoir computer. After grasping an object, the arm is excited by a fixed shaking input at its base, and the resulting ringdown response is recorded through either camera tracking or embedded sensors. Because the input is held cons...

• 4.ForeTac-VLA: A Forecasting-Based Tactile-Vision-Language-Action Model for Contact-Rich Robotic Manipulation

  arXiv:2609.20980v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated strong capabilities in robotic manipulation, yet their reliance on visual perception limits robustness in contact-rich environments, where critical physical interaction states may not be visually observable. Existing tactile-enhanced VLA methods improve physical grounding using observed tactile feedback, but most remain largely reactive rather than explicitly modeling how contact may evolve. Therefore, we propose ForeTac-VLA, a forecasting-based tactile-vision-language fusion model that predicts future tactile states to guide action generation. Specifically, ForeTac-VLA encodes recent tactile observations into temporal representations and integrates them with vision-language features through bidirectional cross-attention. Further, a trans...

• 5.PIVOT: Physically Informed Vision-Language Off-Road Traversability for Field Robot Navigation

  arXiv:2609.20983v1 Announce Type: new Abstract: Terrain assessment is a critical capability for off-road mobile robots, enabling safe and reliable navigation through unstructured and geometrically complex environments. Conventional geometry-based terrain assessment is fast to compute but often overly conservative in unstructured environments. We present PIVOT: a Physically Informed Vision-Language Off-Road Traversability navigation system that augments conventional geometry-based planning with vision-language-model (VLM)-based semantic reasoning for field robots. To physically ground this assessment, we quantify how strongly the VLM's predicted traversal energy cost, robot vibration, and wheel slip correlate with real-world measurements and introduce a unified traversability score that weights each modality by its prediction-measurement c...

• 1.Principal component error in high-dimensional factor models

  In a statistical factor model, principal components (or eigenvectors) of a sample covariance matrix serve as estimates of {\it principal directions}, the true drivers of co-movement of a collection of observed variables. We write the often substantial error in these estimates as a sum of two interpretable terms, which we show have almost sure asymptotic limits as the number of variables grows with sample size bounded. This scenario is commonplace in financial economics, genomics, machine learning and signal processing. {\it Out-of-subspace error} measures the distance from an estimate to the subspace spanned by population factor exposures. It can be expressed in terms of data, providing an estimable floor for error. {\it In-subspace error} arises from the fixed sample size of the latent factor returns and cannot be estimated from data alo...

• 2.Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems

  Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unknown. We study the vulnerability of LLM trading stacks to black-box, input-only attacks that enter solely via admissible social-media feeds. We introduce the Generic Multi-Agent Trading System (GMATS), a framework that captures modern multiagent trading architectures and instantiate a class of black-box poisoning attackers that treat an LLM as a post generator and inject budget-constrained, plausibly benign social-media content into the analyst's evidence stream. We define contagion metrics that trace how adversarial content propagates through the stack, including belief-shift scores at analyst and coordinator layers and attack-clean deltas on standard backtest metrics....

• 3.SAiFE-gym: Model-based Environments for Automated Market Making with Concentrated Liquidity

  We present SAiFE_gym, a Python module that provides a collection of simulation environments for studying trading problems in Constant Product Markets (CPMs) with Concentrated Liquidity (CL). These markets give Liquidity Providers (LPs) granular control over how their capital is allocated and enable them to adjust their range of liquidity provision dynamically based on market conditions, which in turn, dictates how they earn fees. We decompose the microstructure of CPMs with CL in interactive components that allow researchers and practitioners to capture various economic settings. We employ a vectorized approach to optimize our environments, making them scalable for high dimensional Reinforcement Learning (RL) workflows that best describe sequential decision problems. We demonstrate the benefits of our environments by evaluating the perfor...

• 4.Design of a Deep Learning Credit Risk Early Warning System Integrating Multi-source Heterogeneous Data

  Advancements in data fusion and real-time analytics technologies have opened new avenues for addressing complex domain challenges. Financial risk early warning systems often suffer from inefficiency due to information silos and monitoring delays. This paper proposes a credit risk early warning system based on heterogeneous information fusion. The system employs a model architecture integrating deep neural networks and attention mechanisms to extract multidimensional features from diverse data sources such as transaction behaviors and social networks, thereby establishing an early identification mechanism for corporate and individual credit risks. System testing demonstrates that this approach significantly enhances the accuracy and timeliness of risk warnings, outperforming traditional rule-based engine solutions. The findings offer innov...

• 5.WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion

  Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), channel-indiscriminate multi-scale decomposition that conflates heterogeneous frequency signatures, and static multi-branch fusion that cannot adapt to market regime shifts. WaVeFuse addresses these limitations through a unified dual-branch architecture. Symlet-4 wavelet denoising (level 2, MAD soft threshold) suppresses microstructure noise in OHLCV. Seven low-lag TIs computed from denoised prices are encoded by a causal channel-wise continuous wavelet transform (Morlet, 32 scales) into a per-timestep scale-space matrix. A CNN-BiLSTM branch captures temporal dynamics, while a dual-layer Transformer (heads=4, dk in {16, 32}) models inter-scale spectral dependencies, and their representations a...

• 1.GSMA and PDAA Unveil Roadmap to Close Africa’s Mobile Internet Usage Gap and Connect One Billion People by 2030

  Summary available at source link.

• 2.From Pilots to Practice: Closing the Advanced Connectivity Gap in Healthcare

  Summary available at source link.

• 3.Digital Reforms Could Connect Over 1 Million More People to Mobile Internet in Rwanda, GSMA Finds

  Summary available at source link.

• 4.GSMA warns of emerging global AI divide as three billion people remain offline and smartphone component costs soar

  Summary available at source link.

• 5.GSMA calls for greater renewable energy access to enable mobile industry’s net zero transition in Asia Pacific

  Summary available at source link.

• 1.Supporting Industrial Test-Failure Analysis with LLM-Based Systems: An Experience Report

  This study examines tool-augmented Large Language Model (LLM) systems for supporting Root Cause Analysis (RCA) of nightly test failures at Westermo Network Technologies AB. Nightly test executions produce heterogeneous test data and logs that practitioners currently inspect manually across multiple sources. We implemented an RCA workflow in single-agent and orchestrated multi-agent configurations, both with access to test metadata and logs. An exploratory industrial case study used two real failure scenarios. Six practitioners evaluated the scenario reports through a survey and focus group, and operational measurements were collected from 120 repeated executions. The evaluation covered practitioner-perceived correctness, reasoning quality, fix realism, clarity, usefulness, and trust, as well as cost, duration, and consistency. Neither con...

• 2.SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference

  Running large language models (LLMs) locally continues to be limited by restrictions of compute and memory on consumer hardware. The popular acceleration technologies, such as quantization, speculative decoding, and adaptive inferencing, offer substantial speed boosts but usually necessitate retraining, per architecture tuning, or draft models. SpecQuant is a trainingfree framework, that combines speculative decoding with multiparent quantization to perform adaptive, efficient inference of LLMs. SpecQuant derives multiple quantized variants (INT4, FP8, FP16) from a shared base model, and dynamically routes queries based on predicted complexity; lightweight variants are used for simple or factual tasks, and full-precision models are used for complex reasoning tasks or long-context inputs. The shared-weight design of SpecQuant ensures suffi...

• 3.DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning

  Despite the remarkable progress in Multimodal Large Language Models (MLLMs), prevailing Chain-of-Thought (CoT) paradigms remain confined to the natural-language expression space. Consequently, they inherently incur excessive linguistic overhead, leading to information dilution and weak visual grounding. To address this challenge, we propose Dense Reasoning Trace (DRT), a paradigm that departs from natural-language-centered CoT by expressing reasoning as compact structured traces, which include concise intermediate states with symbolic connectors and disentangle visual observations from logical deductions. First, we introduce the Dense Trace Initialization to internalize the DRT reasoning mode into the model, substantially improving token efficiency while preserving visual evidence. To further enable the model to faithfully capture the log...

• 4.MIRAGE: Multi-Perspective Creative Language Model Reasoning with Reinforcement Learning Guidance

  Recent advances in Large Language Models (LLMs) have revolutionized artificial intelligence and how human interact with AIs. Despite impressive advancements, LLMs struggle with complex mathematical, scientific, and logical tasks. Inspired by human cognitive flexibility - our ability to dynamically switch mental perspectives - we propose MIRAGE (Multi-perspective Inference-time Reasoning via Agent-Guided Exploration), a novel inference-time creative thinking framework. MIRAGE includes a Selector that prioritizes effective conceptual perspectives (e.g., algebraic, probabilistic) and a Reasoner that sequentially solves tasks until a confident solution emerges, otherwise aggregating multiple perspectives. Tested on GSM8K, MATH500, MMLU-Pro, and Game-of-24 benchmarks, MIRAGE consistently outperforms methods like Chain-of-Thought and diverse pr...

• 5.PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design

  Multimodal large language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whether an engineering design will work when executed. Existing benchmarks assess spatial reasoning, structural validity, or physics-grounded construction, but they do not determine whether MLLMs can synthesize complete load-bearing structures and repair them after simulator execution exposes a failure. We introduce PolyBridgeBench, an executable benchmark for multimodal bridge design. A model receives a visual scene and structured engineering constraints and generates a complete node--member--material topology. Deterministic legality checks gate execution in a native dynamic physics simulation. Following an execution failure, the benchmark returns temporal visual evidence from the failed roll...

• 1.Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

  Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes admit no reliable programmatic oracle. We introduce a continual adaptation framework in which a frozen frontier model operates professional design software through more than 230 tools, while an external procedural memory of natural-language skills accumulates and refines reusable design procedures from experience. The memory widens by acquiring procedures for recurring uncovered subtasks and deepens by revising existing procedures against their own successful and failed executions, while a matched replay gate admits only changes that repair failures without regressing observed successes. Five rounds over 1,406 real user briefs and 1,869 automatically graded trajectories, with no weight up...

• 2.Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation

  Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the policy to learn both task strategy and low-level motion generation. In this setting, the action representation is critical because it determines how policy outputs are converted into robot motion, shaping both exploration and physical execution. Direct Cartesian command interfaces require the policy to generate motion at every decision step, coupling task-level adaptation with continuous low-level control and increasing the learning burden. We propose PA-RL, a reinforcement-learning framework that uses artificial potential fields as the action representation. Instead of commanding motion directly, the policy adapts the parameters of an energy-like potential field, which generates a state-dep...

• 3.2D GauSS-MI: Efficient Active Scene Reconstruction with Balanced Visual and Geometric Quality

  Active reconstruction requires efficient active view selection to achieve high-quality reconstruction within limited onboard computational resources. Existing methods face challenges in adequately balancing visual and geometric quality with the computational efficiency required for real-time operation. In this work, we present an active reconstruction framework based on 2D Gaussian Splatting (2DGS). We develop an efficient online 2DGS mapping pipeline for incremental RGB-D observations and introduce a probabilistic reliability model that characterizes the view-dependent reconstruction quality of individual 2D Gaussian splats. Building on this model, we formulate 2D Gaussian Splatting Shannon Mutual Information (2D GauSS-MI), a mutual-information-based metric that exploits the explicit surface orientation of 2DGS to evaluate the expected i...

• 4.Multiclass Semantic Segmentation of Wildland Fire Images Using Context-Aware Centralized Copy-Paste Data Augmentation

  Producing accurate annotations for deep learning based image segmentation is both costly and labor intensive. This challenge is especially evident in wildland fire applications, where accurately labeled datasets are scarce due to the difficulty of collecting and annotating dynamic fire scenes. To address this problem, our previous work introduced the Centralized Copy-Paste Data Augmentation (CCPDA) method for semantic segmentation of wildland fire imagery, which generates artificial training samples by randomly pasting fire clusters from source images onto target images. However, random placement can produce contextually unrealistic scenes, such as fire burning on asphalt. In this paper, we present a context-aware strategy designed specifically to improve data quality and realism in small multiclass wildland fire datasets, ensuring that a...

• 5.Chronicle: Cut-Point Replay for Regression Testing of LLM Agents

  Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitwise reproducible, on tools that read changing state, and on a multi-step trajectory that a re-run rarely repeats. Record-and-replay makes a run reproducible, but existing agent tooling records runs only to trace or score them, not to test a code change against them. We present Chronicle, which records an agent run at its non-deterministic boundaries as immutable envelopes and replays it from the record. Its central operation, cut-point replay, serves a chosen subset of boundaries from the record and executes the complementary subset live with new code, turning a recorded incident into a regression test that runs in continuous integration. On a benchmark of 6 recorded failures with simulated ...

• 1.Parallel Reads and Write Optimization for Large-Scale Data Replication

  This White Paper gives data engineers and architects a practical overview of how parallel partitioned reads, write-path optimization, and cloud-native bulk loading reduce large-table replication times, and why replication speed has become a business concern as data volumes grow. Download this free whitepaper now!

• 2.Rethinking Robot Safety in the Age of AI

  This article is brought to you by VicOne . Robot safety has traditionally asked: Can a machine remain safe when something goes wrong? Physical AI raises a harder question: Can a machine remain safe when an attacker changes what it sees, decides, or does even when nothing appears to have failed? As AI and robotics continue to advance at an unprecedented pace, modern robots perceive through multimodal sensors, interpret context using AI models, and translate those interpretations into physical action. As they move into dynamic environments, their safety increasingly depends on the integrity of the data guiding their decisions. That dependence creates risks that conventional safety assessments may not fully capture. Recent research has demonstrated that manipulating what a robot sees, hears, or interprets can influence its behavior without r...

• 3.Single-Phase Direct Liquid Cooling Is Proven for the Next Decade of Ultra-Dense Compute

  Learn how single-phase direct liquid cooling manages the rising heat of AI and high-performance computing, and how it compares with two-phase and immersion approaches. Download this free whitepaper now!

• 4.Responsible AI for Higher Education

  This interactive webinar will introduce the different types of AI, address the concerns with AI, share how we IBM are approaching Responsible AI, and offer guidance to students about what they can do - as individuals, and members of their IEEE chapters. Participants will also have the opportunity to to apply the Responsible AI approach to a particular use case - IBM Bob, a software development life cycle agent, and Q&A. This will be an interactive session, so have phones ready to engage! Register now for this free webinar!

• 5.How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip

  On 25 August, OpenAI fully unveiled Jalapeño, the company’s debut AI accelerator chip. Jalapeño delivers up to 13.4 petaflops of 4-bit compute and accesses 232 gigabytes of the most advanced memory available, linking to it at a blazing 15.4 terabytes per second. Benchmarks cited by OpenAI show that Jalapeño can reduce end-to-end latency (the time between prompt to last token) by up to 3.6 times when compared to Nvidia’s GB300 —a chip the company currently relies on—and do so while consuming less power. Whether these figures translate into real-world gains once Jalapeño enters widespread service in OpenAI’s inference fleet remains to be seen, but performance is only half the story. The other half is how the chip was designed—a process which, as you might expect, was accelerated by OpenAI’s large language models (LLMs). Jalapeño moved from ...

• 1.Further results on AI and labor market reallocation

  This paper documents how artificial intelligence has affected stocks and flows in the U.S. labor market. Combining CPS and JOLTS data with AI exposure and adoption measures from OpenAI and Lightcast, respectively, we construct labor force stocks, worker flows, and market tightness by AI exposure and adoption. Since the introduction of LLMs, workers with high […]

  The post Further results on AI and labor market reallocation appeared first on Marginal REVOLUTION.

• 2.Monday assorted links

  1. Avi Loeb video on UAPs. 2. “[The Mises] library now has a permanent independent home: https://freecapitalists.org/. It holds 945 books, 3,374 journal issues and 2,732 recorded lectures, all free, in PDF, EPUB and MOBI, with the rights recorded per work.” 3. “They invited me to come see it for myself at Sopchoppy’s annual worm grunting festival, which […]

  The post Monday assorted links appeared first on Marginal REVOLUTION.

• 3.The Tragedy of Nikole Hannah-Jones

  Nikole Hannah-Jones famously sent her child to a predominantly black/lower-income public school in New York City. Now her child says she shouldn’t have been used as political fodder. The essay makes for hard reading and I acknowledge NHJ’s courage in writing about her mistakes and the cost to her child. The piece is raw and […]

  The post The Tragedy of Nikole Hannah-Jones appeared first on Marginal REVOLUTION.

• 4.Obama on agentic AI

  Obama recently said: “If we are thinking about AI just in terms of how do we cure cancer or get better energy, you can do that without having agentic AI and having it just roaming free in the internet.” As Roon noted: “this sounds completely incoherent to me” From Rob Saker: An agent is a […]

  The post Obama on agentic AI appeared first on Marginal REVOLUTION.

• 5.Sunday assorted links

  1. Nobel Laureates in support of the California billionaire wealth tax include Krugman, Acemoglu, Diamond, Stiglitz, Banerjee, and Duflo (FT). 2. Secretariat as GOAT. 3. Dead brains and the piano?? 4. “A real contribution of AI is showing the critical weaknesses of humans and human structures.”  But can we take it? 5. When did the […]

  The post Sunday assorted links appeared first on Marginal REVOLUTION.

• 1.The New York Fed DSGE Model Forecast—September 2026

  This post presents an update of the economic forecasts generated by the Federal Reserve Bank of New York’s dynamic stochastic general equilibrium (DSGE) model. We describe very briefly our forecast and its change since June 2026. The New York Fed DSGE model expects similar growth, and slightly more persistent inflation, compared to its forecasts in June. r* forecasts are slightly lower for 2026 but higher for the remainder of the forecast horizon.

• 2.Jackson Hole: Exploring the Financial Frontier

  After two days of heady discussions with academics and policymakers from around the world in high-altitude Jackson Hole, Wyoming, I’m now decompressing back at Street Level. The main theme of this year’s Kansas City Fed symposium was financial innovation in the payments space—a fast-evolving topic with major implications for consumers and central bankers alike. In this post, I’ll share some general takeaways from those Jackson Hole talks and highlight related New York Fed research on payments and financial intermediation.

• 3.Are Central Banks Moving Out of Dollar Assets?

  The dollar’s share of global official foreign exchange reserves fell from 64 percent in 2015 to 56 percent in 2025. This downward trajectory is sometimes read as evidence that the dollar’s role in international financial markets is eroding. However, aggregate statistics obscure the composition of changes occurring at the country level. In this post, we show that the aggregate decline is not a systematic global shift away from dollar assets. Rather, the aggregate decline reflects the actions of a handful of large reserve holders, changing either their currency preferences or the size of their reserve portfolio. From the perspective of the cross section of countries holding dollar assets, the dollar’s status in official portfolios is largely intact.

• 4.Businesses Are Using AI to Transform Work, Not Cut Jobs

  The ongoing advancement and adoption of artificial intelligence continues to raise concerns about widespread job losses. Over the past three years, our regional business surveys have asked firms about their AI adoption and its effects on their workforces. This year, we found that AI use among regional businesses has continued to rise sharply, with more than 60 percent of service firms and about half of manufacturers now using AI—a notable increase from 40 percent and 26 percent, respectively, reported in 2025. Despite this rapid adoption, regional firms’ investments in AI are generally modest, usage tends to be concentrated among a small share of workers within firms, and layoffs have remained uncommon. And, while some firms have scaled back hiring due to AI, others have added workers to help them use it. Retraining employees in response ...

• 5.Has Broader Stock Market Participation Changed How Interest Rates Affect the Economy?

  Stock market participation in the U.S. has changed dramatically over the past four decades. In the mid-1980s, fewer than 30 percent of households held equity. By the early 2000s, more than half of U.S. households owned equity, either directly or through mutual funds, 401(k)s, and IRAs. As participation widened, the way stock market fluctuations passed through to household spending may have changed, with potential implications for how the broader economy behaves. An argument can be made that the rise in equity market participation has dampened the response of output to interest rate changes as stock market fluctuations are now spread across a larger share of households, moderating movements in consumer spending, asset prices, and investment spending.

• 1.A Central European Model for EU Growth

  As the European Union struggles to revive growth and loses ground to the United States and China, its economic future looks increasingly uncertain. Central Europe’s experience suggests that reversing that decline will require fostering innovation while helping poorer countries catch up.

• 2.Might Makes Right Will End Pax Americana

  Far from bolstering US dominance, Donald Trump’s embrace of coercive militarism has eroded it. When the distinction between war and peace dissolves into a ceasefire that is neither, and months of bombardment fail to deliver anything like victory, force looks less like strength and more like pointless destruction.

• 3.A Roadmap for the Next UN Secretary-General

  The next UN secretary-general will take over the most prominent position in multilateral governance at a time when multilateralism is arguably at its nadir. Adapting to today’s multipolar reality will require instilling a renewed sense of purpose and demanding more of member states.

• 4.A New World Order Is Not Beckoning

  It does no good to get misty-eyed about the demise of the liberal international “order.” What the world really needs to manage today's biggest risks is a different, more realistic narrative that does not draw a sharp line between a disintegrating ideal and its post-liberal successor.

• 5.What It Means for Global Warming to Exceed 1.5°C

  A sobering new report from the United Nations Environment Programme warns that even if governments deliver on all their existing climate pledges, warming could reach 1.8°C later this century. That means humanity must pivot from simply containing global warming to finding ways to reverse it.

• 1.Ciena sees optical demand accelerating as AI drives DC expansion

  Ciena said it has secured supply to support at least 30% revenue growth going into 2027 and believes it has secured enough supply to extend that 30% growth trend through…

• 2.The long hike for telecoms (Telco Diary)

  From the newsletter (September 18; sign-up or follow if you want it sooner): AI may be making telecoms look increasingly central to the next digital economy, but updates on the…

• 3.Zayo locks in fiber supply as AI infrastructure demand intensifies

  Troy Lupe, chief network officer at Zayo told RCR that the recently announced expanded strategic supply agreement with Corning secures a significant portion of the fiber optic cable it expects…

• 4.IRIS² takes shape as Europe puts €15.6bn satellite plan into orbit

  Europe’s €15.6bn IRIS² initiative is moving from sovereign-connectivity ambition to hardware, with hundreds of LEO and MEO satellites, billions in industrial contracts and a separate Low-LEO pipeline taking shape. In…

• 5.The 4GHz AI case has a way to go (Telco Diary)

  From the newsletter (September 17; sign-up or follow if you want it sooner): AI is strengthening the case for more mid-band spectrum, particularly as physical AI pushes more traffic upstream.…

• 1.Source Error

  Check Feed

• 1.Goal-Oriented Communication and Control Co-Design via Semantic Push-Pull in Industrial IoT

  Emerging 6G industrial IoT architectures require wireless networked control systems capable of stabilizing diverse control loops over tightly constrained radio resources. Conventional periodic and Age-of-Information (AoI) based scheduling guarantees bounded staleness at the cost of persistent channel saturation. Conversely, pure event-triggered (PureET) strategies minimize transmissions but risk catastrophic silent deterioration when local sensor-side thresholds fail to reflect critical state evolution. To bridge this gap, we propose a communication-control co-design framework governed by a 6G Semantic Layer that independently arbitrates uplink and downlink resources. Instead of relying on freshness, our architecture evaluates the actual control impact of a packet using the state-to-error ratio (SER). We unify this control confidence with...

• 2.SpaceDiffusion: Over-the-Orbit Diffusion for Space Generate-and-Forward Communications

  Satellite communications are an essential component of sixth-generation (6G) mobile networks, which provide ubiquitous connectivity for global services. However, the satellite uplink remains a critical bottleneck for ground devices: their limited transmit power and antenna apertures result in low data rates and high packet errors. To overcome this bottleneck, this paper advocates a novel relaying paradigm termed generate-and-forward (GF) communications, where satellites exploit on-orbit generative artificial intelligence (AI) to robustly reconstruct corrupted data prior to forwarding. Specifically, we propose SpaceDiffusion, an over-the-orbit diffusion framework for satellite-assisted image transmission. The core of this framework is a channel-distortion-aware diffusion theory developed using the following approach. By formulating the rec...

• 3.Common Randomness: A Key Enabler of Trustworthy 6G Communication Systems

  Common randomness (CR) is a valuable resource for enhancing the trustworthiness of 6G communication systems. This article highlights the role of CR in improving scalability, security, and resilience in distributed 6G architectures. It provides an overview of information-theoretic two-source models for CR generation and summarizes known capacity results, together with their implications for practical systems under different communication settings, including one-way, two-way, helper-assisted, and interactive scenarios. Furthermore, the article explores CR-assisted secure identification over Gaussian channels as an application and highlights selected open research problems in CR generation for next-generation wireless systems. The article targets researchers and practitioners interested in bridging information-theoretic tools with emerging 6...

• 4.Jamming Detection in 5G/6G Networks: From O-RAN Concept to OCUDU Deployment

  RF jamming poses a severe threat to 5G/6G networks, increasing packet latency being especially disruption to mission-critical URLLC services. This paper introduces a proactive Jamming Detection xApp (JD-xApp) for the Open RAN architecture that detects attacks by monitoring the moving-average Block Error Rate (BLER) via the E2 interface. Upon detection, the algorithm overrides standard link adaptation, enforcing a robust upper ceiling on the Modulation and Coding Scheme (MCS) to stabilize latency. To counter O-RAN platform adoption challenges, we transition the framework to an open-source Centralized Unit/Distributed Unit implementation (OCUDU). Evaluated with high-end Keysight lab equipment including the UXM 5G Wireless Test Platform and the PROPSIM F64 channel emulator, the JD-xApp reduces the expected number of packet retransmission att...

• 5.Autonomy in Check: Governor-Mediated Adaptive Security at the Edge

  Adaptive security at the network edge increasingly relies on automated planners, including rule-based controllers, learned policies, and LLM-assisted agents, that translate observations into enforcement actions. Once such a planner can influence live policy state, syntactic validity is not enough. A semantically wrong action, produced from incomplete or manipulated observations, can be faithfully executed by an enforcement substrate that cannot judge mission context. We address this problem by treating the boundary between planner output and kernel enforcement input as the primary security object. We propose a split-control architecture in which an untrusted planner emits typed security intents, a deterministic governor checks each intent against safety, resource, temporal-stability, and proportionality invariants, and only admitted actio...

• 1.No new articles

  Summary available at source link.

• 1.Principal component error in high-dimensional factor models

  In a statistical factor model, principal components (or eigenvectors) of a sample covariance matrix serve as estimates of {\it principal directions}, the true drivers of co-movement of a collection of observed variables. We write the often substantial error in these estimates as a sum of two interpretable terms, which we show have almost sure asymptotic limits as the number of variables grows with sample size bounded. This scenario is commonplace in financial economics, genomics, machine learning and signal processing. {\it Out-of-subspace error} measures the distance from an estimate to the subspace spanned by population factor exposures. It can be expressed in terms of data, providing an estimable floor for error. {\it In-subspace error} arises from the fixed sample size of the latent factor returns and cannot be estimated from data alo...

• 2.Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA

  Frontier models score well on shallow document/chart reading tasks. In a controlled data-room audit, moving evidence into buried conditions reduced accuracy, increased forced declarations, increased tool calls, and increased cost per correct answer. Confidence and benchmark calibration did not fully capture wrong answers; a documented production incident shows fabricated structural claims can be mixed with accurate numeric tables. Agentic evaluations need claim-level receipts (statement-level provenance, not answer-level scores), condition-aware scoring, and human-adversarial verification - an auditing discipline, not a leaderboard. The setting we measure is financial due diligence; the setting we are building toward next is defense staff work, where the same buried-evidence shape appears. In both, the model is not a party to the conseque...

• 3.Gate Design and Stage-Dependent Incentives in Retail Proprietary-Trading Evaluations: Why Passing Is Not Standalone Evidence of Skill, and Why the Product Fails to Pay Under Measured Trading Constraints

  Retail proprietary-trading firms sell a two-stage product: a paid evaluation that must reach a profit target before breaching a trailing drawdown, then a funded account that must survive a minimum window and a consistency rule before a payout. We show the geometry of this contract creates incentives that differ by stage and make passing a poor standalone signal of skill. Under end-of-day trailing the evaluation rewards a fast, lumpy cadence while the funded account punishes it, by a factor of nine in the joint gate. The evaluation is defeatable at zero skill: position sizing alone yields a pass probability near 0.40, against a measured cohort rate of 0.168. Pass probability rises with skill, but a real edge and aggressive sizing move it by nearly the same amount, so a pass rate confounds the two. Under a simplified contract model the sell...

• 4.WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion

  Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), channel-indiscriminate multi-scale decomposition that conflates heterogeneous frequency signatures, and static multi-branch fusion that cannot adapt to market regime shifts. WaVeFuse addresses these limitations through a unified dual-branch architecture. Symlet-4 wavelet denoising (level 2, MAD soft threshold) suppresses microstructure noise in OHLCV. Seven low-lag TIs computed from denoised prices are encoded by a causal channel-wise continuous wavelet transform (Morlet, 32 scales) into a per-timestep scale-space matrix. A CNN-BiLSTM branch captures temporal dynamics, while a dual-layer Transformer (heads=4, dk in {16, 32}) models inter-scale spectral dependencies, and their representations a...

• 5.Special Markowitz: Thermodynamic Formalism for the Joint Regularisation of Returns and Covariance

  Special Markowitz (SM) regularises returns and covariance jointly, relative to a reference state (mu_ref, Sigma_ref). Each eigendirection of the whitened relative operator carries a signed spectral potential Phi_k, with persistence factor psi_k = exp(-Phi_k) > 0. Positive potentials attenuate empirical deviations from the reference geometry, zero potential preserves them, and negative potentials amplify them. The persistence factor psi_k governs both the return signal and the covariance deviation: the regularised deviation from the reference is psi_k times the empirical deviation. The logarithmic potential coordinate is characterised by a multiplicative composition law on the multiplicative group of positive real numbers; the Stein loss is characterised as the unique free-energy density (within a natural class) compatible with the resu...

• 1.Goal-Oriented Communication and Control Co-Design via Semantic Push-Pull in Industrial IoT

  Emerging 6G industrial IoT architectures require wireless networked control systems capable of stabilizing diverse control loops over tightly constrained radio resources. Conventional periodic and Age-of-Information (AoI) based scheduling guarantees bounded staleness at the cost of persistent channel saturation. Conversely, pure event-triggered (PureET) strategies minimize transmissions but risk catastrophic silent deterioration when local sensor-side thresholds fail to reflect critical state evolution. To bridge this gap, we propose a communication-control co-design framework governed by a 6G Semantic Layer that independently arbitrates uplink and downlink resources. Instead of relying on freshness, our architecture evaluates the actual control impact of a packet using the state-to-error ratio (SER). We unify this control confidence with...

• 2.SpaceDiffusion: Over-the-Orbit Diffusion for Space Generate-and-Forward Communications

  Satellite communications are an essential component of sixth-generation (6G) mobile networks, which provide ubiquitous connectivity for global services. However, the satellite uplink remains a critical bottleneck for ground devices: their limited transmit power and antenna apertures result in low data rates and high packet errors. To overcome this bottleneck, this paper advocates a novel relaying paradigm termed generate-and-forward (GF) communications, where satellites exploit on-orbit generative artificial intelligence (AI) to robustly reconstruct corrupted data prior to forwarding. Specifically, we propose SpaceDiffusion, an over-the-orbit diffusion framework for satellite-assisted image transmission. The core of this framework is a channel-distortion-aware diffusion theory developed using the following approach. By formulating the rec...

• 3.Common Randomness: A Key Enabler of Trustworthy 6G Communication Systems

  Common randomness (CR) is a valuable resource for enhancing the trustworthiness of 6G communication systems. This article highlights the role of CR in improving scalability, security, and resilience in distributed 6G architectures. It provides an overview of information-theoretic two-source models for CR generation and summarizes known capacity results, together with their implications for practical systems under different communication settings, including one-way, two-way, helper-assisted, and interactive scenarios. Furthermore, the article explores CR-assisted secure identification over Gaussian channels as an application and highlights selected open research problems in CR generation for next-generation wireless systems. The article targets researchers and practitioners interested in bridging information-theoretic tools with emerging 6...

• 4.Jamming Detection in 5G/6G Networks: From O-RAN Concept to OCUDU Deployment

  RF jamming poses a severe threat to 5G/6G networks, increasing packet latency being especially disruption to mission-critical URLLC services. This paper introduces a proactive Jamming Detection xApp (JD-xApp) for the Open RAN architecture that detects attacks by monitoring the moving-average Block Error Rate (BLER) via the E2 interface. Upon detection, the algorithm overrides standard link adaptation, enforcing a robust upper ceiling on the Modulation and Coding Scheme (MCS) to stabilize latency. To counter O-RAN platform adoption challenges, we transition the framework to an open-source Centralized Unit/Distributed Unit implementation (OCUDU). Evaluated with high-end Keysight lab equipment including the UXM 5G Wireless Test Platform and the PROPSIM F64 channel emulator, the JD-xApp reduces the expected number of packet retransmission att...

• 5.Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum

  As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large language models (LLMs) execute multi-step reasoning, invoke diagnostic tools, retrieve domain knowledge, and coordinate across agent teams, are increasingly embedded across the edge-cloud continuum. While the biological brain accomplishes complex cognition on an exceptionally modest metabolic power budget of approximately 20W contemporary LLMs are profoundly energy- and memory-intensive, making sustainable lifecycle orchestration a critical operational priority. However, existing AI lifecycle metrics evaluate only isolated, single-model inferences or overlook multi-agent execution graphs entirely. Consequently, network operators lack foundational models to determine whether distributed agent com...

• 1.Pattern-Aware Virtual Network Embedding Optimization for Cloud Data Centers

  The network virtualization (NV) technology has enabled the sharing of multiple resources among virtual networks (VNs) in cloud data centers. One of the key challenges is to allocate resources in real-time for virtual network request (VNR), which is known as online virtual network embedding (VNE). However, the existing online VNE methods do not exploit the multi-dimensional complementary relationship among diverse VNRs, resulting in the fragmentation and waste of substrate resources. In this paper, we propose the pattern matching based online VNE approach by constructing appropriate matching rules among observed patterns to maximize resources utilization. We devise the clustering based VNRs quantization method and conduct rigorous study on the pattern combination filtering problem. Then, we utilize the column generation to solve it and con...

• 2.Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN

  The O-RAN control plane is becoming agentic: autonomous AI agents, deployed as rApps by different vendors, independently close control loops over shared radio resources. We demonstrate on a live O-RAN system that this independence is unsafe. Two agents with individually correct objectives, one protecting a latency SLA and one maximizing utilization for energy efficiency, jointly drive recurring opposing excursions of the shared resource partition that neither produces alone. Existing conflict-mitigation mechanisms presume a statically known application population and cannot govern agents whose behavior emerges at run time. We present AURA, a lightweight arbitration layer that admits agent actions only when they satisfy feasibility invariants, per-variable dwell times, and a deadband, and we prove the arbitrated system converges to a feasi...

• 3.Jamming Detection in 5G/6G Networks: From O-RAN Concept to OCUDU Deployment

  RF jamming poses a severe threat to 5G/6G networks, increasing packet latency being especially disruption to mission-critical URLLC services. This paper introduces a proactive Jamming Detection xApp (JD-xApp) for the Open RAN architecture that detects attacks by monitoring the moving-average Block Error Rate (BLER) via the E2 interface. Upon detection, the algorithm overrides standard link adaptation, enforcing a robust upper ceiling on the Modulation and Coding Scheme (MCS) to stabilize latency. To counter O-RAN platform adoption challenges, we transition the framework to an open-source Centralized Unit/Distributed Unit implementation (OCUDU). Evaluated with high-end Keysight lab equipment including the UXM 5G Wireless Test Platform and the PROPSIM F64 channel emulator, the JD-xApp reduces the expected number of packet retransmission att...

• 4.Open-source emulation-based test environment to settle O-RAN-compliant trials

  Experimental tools are a key factor in both academic and industrial research communities to create design evaluations of new networking technologies that involve troubleshooting or changing the planning of deployed networks. Physical Software-Defined Radio (SDR) experimental platforms enable a design solution for the quick prototyping of wireless communication systems. However, SDR-based experimental platforms incur high costs, which leads to scalability limitations in the experimental settings. Having said this, network simulators, emulators, and new testbeds have attracted increasing attention. Emulation-based research prototyping can be distinguished from real communication networks and SDR-based platforms by allowing a tradeoff between cost and flexibility. This paper examines the Mininet-RAN emulation tool, which, as well as Radio Ac...

• 5.The Price of the Golden 6G Band: Evaluation of Beam Management Effort in FR3

  Frequency Range 3 (FR3), 7.125-24.25 GHz, regarded as the "golden band" for 6G networks, has less challenging propagation characteristics than FR2 while offering much wider bandwidth for high data rate applications than FR1. Reusing existing FR1 infrastructure for FR3 network deployments requires gNodeBs (gNBs) to employ antenna arrays and perform beam management, which has proven challenging at FR2. In this paper, we extensively study and characterize the beam management effort in an FR3 urban network, in terms of: beam alignment sensitivity, number of directional link opportunities, gNB handover and beam switch rates, and beam steering distance. Our results show that achieving a high and stable mobile throughput requires significant beam management effort across FR3 bands. While the beam tracking requirements are less stringent at the l...