Key Takeaways

• Specialization models improve coordination of agentic software development tools significantly. Studies indicate that coordinating large language model-based tools through this framework enhances overall system efficiency The Role Specialization Model (RSM): Coordinat….
• Runtime contracts are essential for maintaining agent safety in dynamic environments. Research suggests that treating safety as a contractual obligation during execution mitigates common vulnerability risks Agent Safety Should Be a Runtime Contract.
• Uncertainty sampling methods struggle when bounded label noise is present. Current testing reveals that error exposure and location identification degrade under these specific conditions Hard Cases, Bad Labels: Testing Error Exposure….
• Arabic-centric open large language models face unique localization challenges. New family releases aim to address gaps in non-English data representation within global repositories Jais 2: A Family of Arabic-Centric Open Large ….
• Flow matching techniques enable efficient generation of limit order books. This approach offers controllable and efficient methods for simulating complex market dynamics FlowLOB: Efficient and Controllable Limit Orde….
• Post-training quantization affects financial time-series forecast calibration significantly. Evaluations show that past-based calibration bets require careful adjustment after compression steps Calibration Bets on the Past: Post-Training Qu….
• Circularity services launch to help operators reduce electronic waste effectively. Industry alliances are launching specific programs to unlock value from recycled components and materials GSMA Industry Services Launches Circularity Se….

Executive Summary

Today's independent report highlights critical advancements in artificial intelligence infrastructure, specifically regarding the integration of specialized coordination models within agentic software frameworks. The industry is simultaneously addressing hardware constraints for next-generation 6G systems while developing predictive simulation tools necessary for both 5G-Advanced and future 6G networks. On the economic front, mobile operators are pivoting toward circularity initiatives to manage e-waste and secure new value streams, with projections indicating substantial contributions to regional economies by 2030. Technical developments also focus on robust regression methods and knowledge transfer strategies that operate without additional training data, leveraging activation-guided pruning techniques across varying model scales. Safety remains a paramount concern, with renewed emphasis on runtime contracts and rigorous testing of uncertainty sampling under noisy label conditions. Furthermore, the sector is seeing a push for localization in Arabic-centric language models and improved spatial reasoning capabilities for autonomous navigation systems. These developments collectively underscore a shift toward more resilient, safe, and specialized AI applications that bridge the gap between theoretical potential and practical deployment constraints in high-stakes environments like finance and telecommunications.

Coordinating Agentic Tools

The adoption of specialization models for coordinating large language model-based tools in software development is rapidly gaining traction as a viable exploratory case study method. Research indicates that these models facilitate better orchestration of heterogeneous agents, allowing them to work more efficiently on complex tasks without direct human intervention. However, the deployment requires careful attention to runtime contracts to ensure safety protocols are embedded directly into the execution flow rather than treated as an afterthought. This approach represents a significant shift from monolithic architectures toward modular systems that can self-correct and adapt to changing requirements in real-time scenarios The Role Specialization Model (RSM): Coordinat… Agent Safety Should Be a Runtime Contract.

Uncertainty and Safety Testing

Testing error exposure and location becomes particularly difficult when systems operate under bounded label noise, creating challenges for robust uncertainty sampling. Existing methodologies often fail to distinguish between true model limitations and data imperfections, leading to skewed confidence intervals in critical applications such as healthcare diagnosis or financial forecasting. Addressing these issues requires new benchmark suites that specifically isolate the effects of noisy labels on downstream agent performance. Without these rigorous tests, organizations risk deploying agents that appear reliable but fail catastrophically when faced with slightly altered input distributions Hard Cases, Bad Labels: Testing Error Exposure….

Limit Order Book Generation

Flow matching has emerged as a promising technique for generating limit order books efficiently and controllably within high-frequency trading simulations. By utilizing flow matching, researchers can create synthetic market data that preserves key statistical properties of real exchange feeds while allowing for controlled parameter variations. This capability is vital for stress-testing algorithmic trading strategies against extreme market events without risking actual capital. The ability to generate these structures on demand significantly accelerates the development cycle for next-generation quantitative models FlowLOB: Efficient and Controllable Limit Orde….

Arabic-Centric Model Development

The release of new family models focused on Arabic-centric data aims to address long-standing representation gaps in global large language model repositories. These models are designed to handle contextual nuances specific to Levantine and Maghrebi dialects while maintaining high accuracy on standardized benchmarks. Developing such specialized assets requires substantial local data curation efforts that differ significantly from English-centric approaches. The success of these initiatives will likely depend on community-driven contributions that ensure the training data reflects diverse usage patterns across the Arab world Jais 2: A Family of Arabic-Centric Open Large ….

Financial Time-Series Forecasting

Post-training quantization methods applied to financial time-series forecasting present challenges regarding calibration accuracy when evaluated against historical performance metrics. Quantizing models after the primary training phase can reduce computational costs but often introduces systematic biases that affect the calibration of probability estimates for future market movements. Researchers are now investigating whether these compression techniques degrade the model's ability to predict tail risks accurately, which is critical for risk management functions. Careful validation procedures are necessary to ensure that quantized models retain the predictive fidelity required by institutional investors Calibration Bets on the Past: Post-Training Qu….

Operator Circular Economy Initiatives

Telecom operators are increasingly turning to circularity services designed to help them reduce electronic waste and unlock economic value from discarded hardware. Industry alliances have launched specific programs to facilitate the recycling of copper, gold, and rare earth metals found in aging network equipment. This initiative is expected to contribute billions to regional economies by 2030 as digital trust and sustainability become central themes at major industry summits. Operators investing early in these closed-loop systems stand to gain significant competitive advantages in emerging markets where resource scarcity is becoming a constraint on growth GSMA Industry Services Launches Circularity Se….

Babak's Daily Briefing

Monday, August 17, 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.The Role Specialization Model (RSM): Coordinating LLM-Based Tools in Agentic Software Development - An Exploratory Case Study

  The integration of large language models (LLMs) into software development workflows has given rise to a paradigm known as Agentic Software Engineering (SE 3.0), in which autonomous agents manage full development life cycles under human supervision. This paper presents an exploratory case study in which three LLM-based tools, Antigravity (an agentic IDE with a Gemini 2.5 backend), Gemini CLI, and Qwen Code (local execution via Ollama), are coordinated according to a role-distribution framework proposed in this work as the Role Specialization Model (RSM). Three research questions guide the study: (RQ1) how can LLM-based tools with distinct capabilities be coordinated through the RSM in a real development workflow; (RQ2) what deviations from the planned role distribution emerge during RSM execution and what factors explain them; and (RQ3) ho...

• 2.Agent Safety Should Be a Runtime Contract

  The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI. We argue this is structurally insufficient for autonomous agents that execute code, mutate files, send messages, and modify databases. Agent safety should be a runtime contract enforced by the harness, and the contract has two complementary faces. The preventive face blocks dangerous actions before they happen via sandboxes, permission gates, output filters, and trajectory monitors. The evidential face requires verifiable proof that good actions actually happened, gating task submission on hard evidence such as test runs, log captures, file diffs, and citation grounding. We ground the position in four lines of public evidence, with row-level protocols and data released in the supplementary JSON files: a survey of...

• 3.On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

  Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community has not kept pace. To quantify the state of the field, we conducted a systematic literature review under PRISMA 2020 guidelines across six databases, screening 743 records and retaining 85 papers (2023--2025) on agentic LLM security. Attack research outpaces defense work by 3.9:1. Perception-layer vulnerabilities (prompt injection, jailbreaking, adversarial perturbatio...

• 4.Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases

  As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NLP community typically evaluates models using large, unstructured benchmarks. While effective for general capabilities, these datasets fundamentally conflate causal mechanisms: even when an aggregate bias is detected, unstructured evaluations cannot disentangle whether it stems from baseline traits, contextual confounders, or complex interactions. To address this, we introduce an analytically exact framework for the controlled behavioral evaluation of LLMs. We bridge human psychometrics with LLM mechanics by resolving gaps in design, measurement, and analysis. First, we replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interact...

• 5.Evo-Bench: Can Language Models Improve Agent Harness?

  Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness. However, systematically benchmarking this capability remains challenging, as existing evaluations fail to isolate harness improvements from base model strength, prevent task-specific overfitting, or capture long-horizon iterative research. To address these challenges, we introduce Evo-Bench, the first benchmark designed to evaluate models' intrinsic harness-evolving capabilities across Search, Office, and General agent domains. To rigorously isolate this capability, Evo-Bench employs a novel harness-guided construction framework: it leverages auxiliary-task evolution to identify task...

• 1.Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study

  arXiv:2608.13568v1 Announce Type: new Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto measurable variables, and reports a preliminary s...

• 2.Think in Latent, Explain in Language: Self-Explainable Latent Reasoning

  arXiv:2608.13570v1 Announce Type: new Abstract: Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning into compact embeddings. However, compressing reasoning into the latent space renders the thinking opaque, hindering its interpretability. Current methods present a stark trade-off: they either function as unexplainable ''black boxes'' (e.g., Coconut), where the latent reasoning is not human-readable, or rely on separate post-hoc decoders for explainability (e.g., Heima), introducing architectural overhead and decoupling the explanation from the actual reasoning process. In this work, we present a unified framework for Self-Explainable Latent Reasoning (SELR) that trains a single model to perform efficient and in...

• 3.Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems

  arXiv:2608.13571v1 Announce Type: new Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true workflow cost to single-call cost. Systems like FrugalGPT route based on the latter, which can underestimate real cost by more than $2\times$ on difficult tasks. We address this with InflationAgent, a four-stage router that (1) measures token inflation systematically across model tiers and task types, finding inflation as high as $4.25\times$ for a 7B model on multi-hop question answering; (2) introduces CoT Branching Entropy (CBE), a pre-execution difficulty signal...

• 4.BCMT: Blockwise Causal Memory Transformer

  arXiv:2608.13578v1 Announce Type: new Abstract: Transformer architectures rely on dense self-attention to model long-range dependencies, but this mechanism exhibits quadratic complexity with respect to sequence length. We introduce BCMT (Blockwise Causal Memory Transformer), an architecture for long-context language modeling that decouples local token interactions from global context propagation. Dense causal self-attention is applied independently within local blocks, while each block produces an adaptive summary aggregated through an exponential causal memory. This memory is subsequently injected back into the token representations, enabling efficient propagation of long-range contextual information without relying on explicit global attention. Unlike standard Transformers and recurrent memory architectures, BCMT maintains neither dens...

• 5.Jais 2: A Family of Arabic-Centric Open Large Language Models

  arXiv:2608.13580v1 Announce Type: new Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competitive 8B-parameter variant among the evaluated open models. A custom Arabic-centric vocabulary enables efficient training and inference. In addition, an optimized architecture and training recipe yield highly compute-efficient training. With a substantially smaller token budget than comparable models, Jais 2 achieves strong Arabic performance on the benchmarks considered in this report and competitive...

• 1.L-FNO: Lorentzian Fourier Neural Operator for Stochastic Event Dynamics

  arXiv:2608.13562v1 Announce Type: new Abstract: Modern operational systems face uncertainty even in routine conditions, where rare, bursty, and self-exciting events emerge from both exogenous covariates and endogenous event dynamics. Standard neural operators are typically trained as regression-style function-to-function models rather than conditional-intensity estimators, limiting their suitability for sparse event regimes. We introduce the Lorentzian Fourier Neural Operator (L-FNO), a stochastic neural operator that combines an FNO-style covariate path, Lorentzian spectral kernels for history-dependent excitation, and a likelihood-based training objective. We evaluate L-FNO on eight synthetic point-process benchmarks and three real-world datasets covering disease outbreak prediction and semiconductor fault or defect detection. L-FNO imp...

• 2.Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required

  arXiv:2608.13566v1 Announce Type: new Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as evidence of broad coding capability, both for research artifacts and user-facing systems. We argue that optimization for these benchmarks leads to measuring task-specific performance, creating a meaning gap between measured scores and claims of general coding ability. We examine this gap with a Django-based case study benchmark suite we create. Evaluating foundation models and checkpoints post-trained on SWE-bench trajectories, we find that benchmark rankings frequently fail to generalize. Post-trained checkpoints show little cross-task transfer, and SWE-bench optimization yields limited or no gains on our tasks or on LiveCodeBench. Similarly, fine-t...

• 3.Robust XGBoosting for Regression

  arXiv:2608.13590v1 Announce Type: new Abstract: XGBoost is a very popular and powerful method for prediction. It iteratively fits simple decision trees to the residuals of the previous step. An efficient and scalable implementation is available. The standard loss function for XGBoost is the quadratic loss, but a Huber loss can also be used. In this paper, we study the robustness of XGBoost and show that its performance can be affected by vertical outliers and leverage points. To address this, we explore alternative loss functions, based on M-, S-, and {\tau} -estimators from robust regression. Our results indicate that a two-step procedure, referred to as MM-XGBoost, provides the best trade-off between robustness and prediction accuracy.

• 4.Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning

  arXiv:2608.13596v1 Announce Type: new Abstract: Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales. We study an underexplored cross-scale setting: improving a small recipient language model with a stronger donor despite substantial architectural mismatch. We ask whether useful capabilities can be transferred without explicit neuron-wise semantic alignment. Building on the observation that truncating a large model to a smaller architecture and injecting it with a tiny mixing weight can already improve the recipient, we propose Activation-Prune-Merge (APM), an activation-guided framework for cross-scale fusion. APM constructs task-conditioned activation maps on the donor, selects salient layers, hidden dimensions, attention heads, and MLP neurons to prune it to the recipient ar...

• 5.Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise

  arXiv:2608.13601v1 Announce Type: new Abstract: Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly. This study tests whether uncertainty sampling fails because it acquires more corrupted labels or because errors concentrated in difficult regions are especially harmful. Margin-based uncertainty sampling is compared with random sampling under clean labels, random classification noise (RCN), and bounded difficulty-dependent noise on three public binary tabular datasets. The design uses 100 paired seeds, nine expected noise rates from 0 to 0.30, annotation budgets from 20 to 120, and logistic regression with regularization re-selected by cross-validation at every budget. An exposure-matched RCN control aligns mean final acquired corruption, whi...

• 1.Adjacency-Based Spectral Proxy Control of Mobile Communication Agents

  arXiv:2608.13616v1 Announce Type: new Abstract: We consider a heterogeneous mobile-agent network composed of uncontrolled task agents and controllable communication agents. The objective is to reposition communication agents online as task agents move. Since throughput-based objectives are generally unsuitable for real-time control, spectral graph metrics such as algebraic connectivity are commonly adopted as surrogate objectives. However, controlling algebraic connectivity relies on the eigenvector corresponding to the second-smallest eigenvalue of a graph's Laplacian matrix (i.e., the Fiedler vector), whose distributed estimation requires an unbounded number of communication rounds to converge. In this work, we identify a structural decomposition of this Fiedler-gradient controller into a local interaction rule and a graph embedding com...

• 2.hint$^2$: Hierarchical World Models for Inference-Time Temporal Logic Guidance

  arXiv:2608.13678v1 Announce Type: new Abstract: A central goal of robot learning is to enable robots to execute rich instructions specified at runtime. Large-scale language-conditioned policies have made substantial progress toward this goal, yet still struggle with temporal structure and safety constraints. Linear Temporal Logic (LTL) provides a powerful language to express complex, non-Markovian instructions. However, guiding learned manipulation policies toward LTL satisfaction remains challenging because modern policies generate short-horizon action chunks and replan in closed loop, while almost all LTL specifications are evaluated over long-horizon trajectories. In this paper, we introduce hint$^2$, a method for guiding short-horizon policies toward satisfying complex LTL specifications at inference time using hierarchical world mode...

• 3.Graph-MambaNav: Spatial-Temporal Graph Mamba Leveraging Object-Relation Knowledge for Object-Goal Navigation

  arXiv:2608.13723v1 Announce Type: new Abstract: Object-goal navigation requires an agent to reason over object relationships and prioritize target-relevant objects for efficient decision making in unseen environments. While existing graph-based methods incorporate target-awareness at the feature or attention level, they remain permutation-invariant and lack an explicit mechanism to control information propagation order, limiting their ability to model target-dependent importance and long-range dependencies. In contrast, Graph-Mamba highlights that node prioritization through sequence ordering is critical for effective global reasoning. In this work, we investigate the node prioritization mechanism in Graph-Mamba and study its role in object navigation. We propose Graph-MambaNav, a target-aware spatial-temporal graph encoding framework tha...

• 4.Knowledge-Data-Dual-Driven Reinforcement Learning for Autonomous Vehicle Control in Mixed Traffic

  arXiv:2608.13878v1 Announce Type: new Abstract: In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges. First, physics-based priors incorporated into reinforcement learning (RL) models fail to capture latent interactive vehicle intentions and diverse driver behaviors, limiting the proactive reasoning capabilities. Second, abrupt maneuvers by surrounding vehicles cause non-stationarity, leaving long-tail safety events under-explored. Third, hybrid action spaces destabilize unified RL training due to the different temporal scales of continuous car-following and discrete lane-changing maneuvers. To address these issues, we propose Knowledge-Data Dual-driven Reinforcement Learning (KDDRL). First, a conditional deep generative model synthesizes intention-aware future trajectories, converting pas...

• 5.Ontology-Grounded World Models for Failure Diagnosis and Closed-Loop Repair in Physical AI Systems

  arXiv:2608.13901v1 Announce Type: new Abstract: EV-WM represents candidate quality with feature and event scores, but these scores do not explicitly record an unmet task predicate, a route label for an available correction mechanism, or a post-correction acceptance result. We present Onto-EV-WM, an ontology-grounded diagnosis and verification-gated correction interface layered above EV-WM rather than a replacement world-model architecture. The implemented task-local TBox defines entity types, predicate signatures, and constraints; source-specific grounding maps predicted or simulator-observed states to task ABoxes; and deterministic rules retain each missing predicate and its arguments when assigning a route label. Learned or heuristic proposers remain separate from this symbolic interface; native task predicates determine acceptance, and...

• 1.Buy the Rumor, Sell the News: When Is News Priced In?

  Two old market sayings hold that news is already priced in by the time it is published, and that the rumor is bought while the news is sold. Both place the price move associated with a piece of news before and at publication rather than after it. Whether the claims hold, for which kinds of news, and by how much are basic questions about how fast markets absorb public information. We test them on 4.57 million financial news articles covering roughly 3,000 US stocks (2023-2026). A large language model teacher, distilled into a compact classifier through active learning, assigns each article one of 17 event tags and five attributes; articles are clustered into stories to separate first reports from follow-up coverage; and beta-adjusted abnormal returns are measured around the resulting 1.68 million stock-day events, with 364,405 neutral-sent...

• 2.FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching

  Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, controllable scenario generation, and the ability to generalize beyond the instruments seen during training---properties that existing agent-based and deep generative simulators provide only partially. We present \textbf{FlowLOB}, a conditional \textbf{flow}-matching generator of \textbf{LOB} trajectories, trained on multiple Hong Kong Exchange (HKEX) symbols at three sampling frequencies ($0.1$s, $1$s, $10$s) in tick-relative representation that transfers to unseen instruments. Because flow and diffusion models admit a common formulation, we train both with identical data, architecture, and budget, and sample both through the same fixed-step ODE solvers, yielding a controlled comparison of sa...

• 3.What Makes a Peer? Valuation-Anchored Similarity in Private Markets

  As more investors contemplate private markets and contend with limited transparency, sparse disclosures, and infrequent transactions, identifying economically meaningful peer companies for comparison is a fundamental challenge for valuation, due diligence, portfolio construction, and risk management. We propose an ensemble tree-based supervised similarity learning framework that defines company similarity through the lens of market valuation rather than static feature matching or semantic descriptions. Specifically, we train a CatBoost gradient-boosted decision tree model on observed private company valuations and derive a valuation-aware similarity metric from importance-weighted leaf-node co-occurrences across the ensemble. The similarity metric captures shared valuation drivers while accommodating nonlinear relationships, mixed data ty...

• 4.DYSANOS Generative Dynamic Smooth Arbitrage-free Non-parametric Option Surfaces

  This article presents with DYSANOS the first generative market model for smooth SANOS option surfaces for all strikes and expiries which are free of static arbitrage. Our model is designed to generate entire paths of daily spot and option prices for years in the future. We present a robust and useful if somewhat simplistic baseline hidden state generative model in the form of an AR(1) model. We discuss model setup, data pipeline, and training and investigate numerical resence of dynamic arbitrage. We illustrate model performance on Option Metrics' IvyDB S\&P Index data from 2020 to~2025 and compare it to a pure implied-vol PCA model.

• 5.Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting

  Financial forecasting models are typically developed in full precision, yet production deployment often requires low-precision inference to reduce memory and computational cost. Post-training quantization (PTQ) enables such deployment without retraining. However, reliable activation quantization requires calibration: activation ranges are estimated from historical data before deployment and then remain fixed during future inference. The importance of this deployment choice for financial forecasting remains poorly understood. We present a systematic study of activation calibration for PTQ in cross-sectional volatility forecasting on the S&P 500. Our evaluation covers seven representative neural architectures, eight walk-forward test years (2018-2025), and 560 trained models. We find that activation calibration has little effect at 8 bits b...

• 1.GSMA Industry Services Launches Circularity Services to Help Operators Reduce E-Waste and Unlock Value

  Summary available at source link.

• 2.GSMA Report: Mobile Industry to Contribute US$1.4 Trillion to Asia Pacific Economy by 2030 as Digital Trust, AI, Digital Sovereignty and Resilience Take Centre Stage at M360 ASEAN

  Summary available at source link.

• 3.African Trust & Safety LLM Benchmark: Stress-testing AI Safety Across Africa’s Languages and Contexts

  Summary available at source link.

• 4.New GSMA Intelligence Research Examines Saudi Arabia’s Mobile Network Performance and Quality of Service

  Summary available at source link.

• 5.Connectivity Plays Its Part: Lessons From 2026 World Cup That Spain Should Consider for 2030

  Summary available at source link.

• 1.SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning

  Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated spreadsheet reasoning remains challenging for large language models (LLMs). Real-world workbooks often contain implicit cross-table associations, fine-grained column dependencies, and complex spatial layouts. Existing methods typically flatten these multidimensional structures into sequential strings, losing important intra-sheet boundaries and inter-sheet semantics. Consequently, LLMs cannot exploit the global spatial context that human experts naturally use when inspecting spreadsheets. We propose SheetCompass, a graph-guided and memory-driven agentic framework for spreadsheet reasoning and automation. SheetCompass explicitly models structural relationships within and across worksheets while maintaining task-relevant information in memo...

• 2.Whose doctor does the AI recommend? An algorithm audit of reputation and demographic signals in large language model-assisted physician choice

  Patients increasingly ask large language model (LLM) assistants which doctor to see, making these systems AI infomediaries: algorithms that intermediate one person's choice among other people and thereby decide, silently and at scale, which physicians become visible. We report a prespecified randomized algorithm audit of what causally moves those recommendations. Seven models (six open-weight; gpt-4o-mini) each chose among five synthetic family-medicine physician cards whose attributes were independently randomized across 3,024 choice sets, three patient personas, nine prompt paraphrases and nine experimental arms, yielding 40,068 scored responses; gender and ethnicity were signaled through names following correspondence-audit methodology. Reputation signals dominate: raising a rating from 3.9 to 4.7 increases choice probability by 31.4 p...

• 3.Spatial Message Passing in Language Space for Pathology Image Interpretation

  Multimodal Large Language Models (MLLMs) can generate pathological descriptions from histological images, but gigapixel Whole Slide Images (WSIs) exceed their visual context limits. The standard tiling workaround makes WSIs tractable yet severs the tissue neighborhoods that define tumor-stroma interfaces and morphology. We introduce Spatial Language Message Passing (SLMP), a framework that performs spatial reasoning entirely in language space, human-readable by construction. SLMP represents a WSI region as a spatial text graph: tiles are nodes initialized with MLLM descriptions, and edges encode spatial adjacency. For each tile, an LLM refines its description by integrating language messages from adjacent tiles under a shared aggregation policy that, on the tile grid, acts as an adaptive local kernel operating on text rather than learned ...

• 4.TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments

  Time series analysis in high-stakes domains relies on recurring data releases, where new observations can alter the evidence base and the validity of later conclusions. Existing time series QA benchmarks mostly rely on fixed snapshots, leaving temporal validity and cutoff-aware evidence use unevaluated. We introduce TimeSage-EV, a live benchmark for agentic time series analysis in evolving environments. It tracks 60 real institutional scenarios across 6 domains, comprising 1,485 scenario-period QA pairs from Feb 2023 to May 2026 and spanning monthly, weekly, daily, and irregular release cadences. At each period, large language model (LLM) agents receive time series data and source reports, while the withheld target release provides ground truth. TimeSage-EV evaluates state identification, data summarization, and outlook reasoning. Experim...

• 5.APTER: Adaptive Post-Training with Expert-Grounded Rubrics

  As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses. Existing post-training methods often rely on holistic preferences or outcome-level verification, while recent rubric-based methods usually generate rubrics independently for each query. In specialized domains, such unconstrained rubrics may omit critical requirements and vary across samples, hindering the diagnosis and targeted repair of persistent capability deficiencies. We propose APTER (Adaptive Post-Training with Expert-Grounded Rubrics), a framework that integrates structured domain knowledge into fine-grained evaluation, optimization, and diagnosis for specialized complex reasoning. First, expert-grounded rubric construction starts from an e...

• 1.CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets

  Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for modern visual content creation. It is currently dominated by generalized methods that fine-tune a pretrained multimodal diffusion transformer (MMDiT) on hundreds of thousands to millions of paired \emph{(reference, composed-target)} examples, where each composed target is a synthesized image of the subject in a novel scene. Producing such targets demands a costly multi-stage curation pipeline---LLM-based prompt generation, T2I-based composed-target synthesis, reference-subject extraction, VLM-based quality filtering, and correspondence labeling---and tightly couples each method to a particular target synthesizer and curation choice. We introduce \emph{CRAFT} (Constr...

• 2.Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based Fine-Tuning Approach

  Recent advances in large language models (LLMs) have reshaped semantic analysis. Opinion Extraction (OE) for Science and Technology Intelligence (STI) requires concise core opinions from large information streams. Off-the-shelf models struggle to filter noise from these streams and show limited structured-output reliability in zero-shot multilingual and multi-modal settings. To address information overload and extraction defocus, this study proposes a multimodal core-opinion extraction framework in which visual evidence serves as a contextual anchor for textual judgment. Using VideoLLaMA2 (VL2) and VideoLLaMA2.1 (VL2.1) as the base models, we apply Quantized Low-Rank Adaptation (QLoRA) fine-tuning on a curated dataset of 2,194 multilingual and multimodal samples. Under the selected Image-Augmented setting, fine-tuned VL2.1 generates struc...

• 3.Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy

  Driven by the attention economy, short-video Recommender Systems (RSs) are primarily optimized to maximize user engagement by promoting videos that capture attention within seconds. These systems inherently favor shallow-content videos that are effective at attracting immediate attention. However, growing evidence suggests that prolonged exposure to such content may negatively affect users' cognitive engagement and mental well-being, raising concerns about the long-term societal impact of the short-video platform. To tackle this challenge, this paper introduces a new metric, the \textbf{Content Depth Score (CDS)}, to quantify the content depth of short videos. CDS measures the extent to which a video is expected to stimulate higher-order cognitive processes, using a seven-level scale grounded in established theories of cognitive psycholog...

• 4.Fashion Outfit Generation via Unified Sequential Composition Models

  The task of synthesizing stylistically coherent fashion outfits from massive item libraries, known as fashion outfit generation, remains a non-trivial challenge, primarily due to the non-monotonic and implicit nature of aesthetic compatibility, coupled with the exponentially large combinatorial search space. In this paper, we formalize this task as Constrained Ensemble Generation (CEG) and model it as a finite-horizon deterministic Markov Decision Process. To address CEG in fashion, we propose the Unified Sequential Composition Model (USCM), which jointly models set-level compatibility and latent composition intents. Guided by USCM's learned priors, a Latent Expansion Monte Carlo Tree Search (LE-MCTS) mechanism is proposed to handle item retrieval during composition, balancing local aesthetic synergy with global structural balance. Extens...

• 5.SNM-VFI: Symmetric Nonlinear Motion-Guided Generative Video Frame Interpolation

  We propose Symmetric Nonlinear Motion-guided Generative Video Frame Interpolation (SNM-VFI), a training-free framework for motion-controllable generative video frame interpolation with pre-trained optical flow and video diffusion models. Unlike conventional diffusion-based VFI methods that synthesize intermediate frames from random noise, SNM-VFI guides the generative process with correspondence-aware frames produced by a symmetric nonlinear motion model. Specifically, we first utilize a pre-trained optical flow model to construct multi-frame nonlinear flow-based intermediate frames and confidence maps. These flow-guided frames are then encoded as latent priors to initialize and iteratively guide a pre-trained Video Diffusion model, enabling the diffusion model to preserve dense motion correspondence while improving perceptual realism. To...

• 1.From AI Copilots to Agent Swarms

  The impact of AI on software development has been both profound and ever-evolving. Last year, I wrote about AMD’s plans to use AI not just for generating new lines of code, but also for other steps in the software development lifecycle (SDLC), such as triaging problems, debugging code, and testing the software. At the time, we were hoping for a 25 percent productivity boost from AI use over the course of two or three years. But with each new release, the capabilities of Large Language Models (LLMs) improve dramatically—accelerating software development, increasing the quality of AI-generated code, and fundamentally reshaping how software is engineered. Now, just one year later, we have surpassed our productivity target, achieving a 30 percent overall productivity boost through AI. On top of that, we are rethinking not only how we use AI w...

• 2.AI Used to Verify Toughest Mathematics Proof Yet

  Representing a significant milestone in AI-assisted mathematical research, a team at Axiom Math has automatically verified the proof of a theorem relating to prime numbers—colloquially referred to as the “246 theorem”—for the first time using the company’s AI system AxiomProver. In formal verification, mathematicians task a computer with checking a machine-readable version of a proof. The process is not a 100 percent guarantee that the proof is correct, as a recent demonstration showed , exposing how a bug in the method could be exploited to accept a false, AI-generated proof. Still, the computational method is as close to a rubber stamp as you can get. This particular verification formalizes an important advance in number theory. Beyond this particular proof, it demonstrates how automated AI verification could be used in the future to en...

• 3.The CPU Comeback Is Upon Us

  Earlier this year, leaders at Amazon Web Services delivered a new mandate to their engineers: they need to conserve CPU cycles at all costs. AWS has reportedly experienced an explosion in wait times for CPU server capacity as AI workloads strain the company’s cloud infrastructure. The issue seemingly took AWS off-guard, and for good reason. The AI boom led to a surge in demand for GPUs and, later, memory . CPUs were mostly left out of the story, as their relative lack of parallelization made them a poor fit for AI model inference, the process of running and serving large language models (LLM) to users. But the rise of agentic AI systems, which allow AI models to operate autonomously and call on sub-agents, is changing the narrative. Matt Kimball , vice president and principal datacenter analyst at Moor Insights & Strategy , says 2026 has ...

• 4.Inside the Data Bottleneck Slowing Visual and Physical AI

  A survey of over 700 professionals examines how visual and physical AI teams build systems, why models fail, and where data work drives production. Download this free whitepaper now!

• 5.Pakistani Judges Give Their Verdict on JudgeGPT

  Judges around the world have made headlines for illicitly using generative AI in their work. But in Pakistan, a large-scale trial of a specially designed AI tool for judges found the technology—together with appropriate training–boosted the number of cases resolved by 6.3 percent with no obvious drop in the quality of judgments. With a backlog of 2.26 million cases and fewer than two judges per 100,000 people—compared to 22 in the EU and eight in Brazil—Pakistan’s judiciary was in sore need of help. So, in consultation with the judiciary, economist Sultan Mehmood , of the New Economic School in Moscow, and collaborators tested whether AI could ease the burden. They built a custom tool combining OpenAI’s GPT-4 large language model (LLM) with a knowledge base of nearly 130,000 Pakistani judicial opinions and statutes, to help judges with le...

• 1.Monday assorted links

  1. Where do the great American comedians hail from? 2. General thoughts on biosafety. 3. “Violet Hensley Dies at 109; Ozarks Fiddler Made Opry Debut at 99” (NYT).  She also handcrafted 73 fiddles, appeared on The Beverly Hillbillies, and considered bluegrass too modern for her.  She had nine children as well. 4. Which campaiging politicians […]

  The post Monday assorted links appeared first on Marginal REVOLUTION.

• 2.What should I ask Roman Mars?

  Yes I will be doing a Conversation with him.  Most of all he is obsessed with design, here is Wikipedia: Roman Mars is an American radio producer. He is the host and producer of 99% Invisible, a KALW radio show and podcast, and a founder of the podcast collective Radiotopia, which he describes as efforts “to broaden the radio landscape [and] make […]

  The post What should I ask Roman Mars? appeared first on Marginal REVOLUTION.

• 3.Somalia facts of the day

  The fruits of better security are plain to see. “Business is booming,” says Gamal Hassan, the commerce minister. New buildings are going up at a frenetic pace. The district around the airport, in particular, has grown much denser (see satellite images). Dahab Tower, a 26-floor confection of luxury flats, a mall, a gym and a […]

  The post Somalia facts of the day appeared first on Marginal REVOLUTION.

• 4.What I’ve been reading

  1. Gerald Martin, Mario Vargas Llosa: A Life.  A good book if you wish to read about his strange sex life, starting early in his years.  But if you are more interested in the history of ideas, Peruvian politics, or the development of the Latin American novel it is far less compelling.  So for me […]

  The post What I’ve been reading appeared first on Marginal REVOLUTION.

• 5.Things you cannot buy in America?

  3. Exterior roller shutters (Rollladen) In much of Europe, homes feature heavy shutters integrated into the exterior of the window, enabling total blackout and better insulation. Sleeping in true, complete darkness—not “blackout curtain” darkness, but can’t-see-your-hand darkness—is an experience most Americans will never have. These shutters are nearly impossible to get in the USA because […]

  The post Things you cannot buy in America? appeared first on Marginal REVOLUTION.

• 1.Does the Equity Term Structure Respond to Monetary Policy Shocks? 

  A long-standing body of research, inspired by Bernanke and Kuttner (2005), has documented the effects of Fed interest rate surprises on stock markets. While stock markets provide valuable information about the investor risk premium and dividend growth expectations, researchers have only recently developed more comprehensive tools to estimate the term structure of equity risk premia and dividend growth expectations across a broad range of maturities. In this post, we investigate the impact of monetary policy surprises (or shocks) on short- and long-term estimates of risk premia and growth expectations through the lens of the Giglio, Kelly, and Kozak (2024) model.

• 2.How Distressed Are Consumers? Reconciling Diverging Credit Card Delinquency Measures

  Total debt balances declined slightly by $13 billion in the second quarter of 2026, according to the latest Quarterly Report on Household Debt and Credit from the New York Fed’s Center for Microeconomic Data. Mortgage and student loan balances saw a small decline, while there were increases across other debt products. Delinquency rates across most products remained fairly stable. Still, between 2022:Q3 and 2026:Q1, the percentage of credit card balances 90+ days delinquent rose from 7.6 percent to 12.8 percent, prompting concerns that Americans are falling behind on their debt payments at ...

• 3.Stripping STRIPs Trading Activity

  In March 2020, the Financial Industry Regulatory Authority (FINRA) began reporting aggregate trading volume for securities issued by the U.S. Treasury Department. The public data do not, however, include information about the trading activity of Separate Trading of Registered Interest and Principal of Securities (STRIPS). STRIPS are created from existing Treasury securities and offer risk […]

• 4.Why Do Fewer Renters Expect to Move?

  Americans are moving less than they used to. Moving rates have declined steadily for decades, falling from close to 20 percent annually in the mid-1980s to below 10 percent by 2019. This decline has persisted through business cycles and has been evident across all regions, and has affected a broad range of demographic groups. Falling mobility matters because moving helps households access job opportunities, adjust to changing circumstances, and improve their housing situations. In this post, we show that the decline in mobility also holds for renters, with growing challenges to owning a home being an important contributing factor.  We use data from the annual ...

• 5.AI’s Impact on Labor and Hiring

  Welcome to Street Level, my new series on Liberty Street Economics. As research director, I try to keep track of the wide range of work that the economists at the New York Fed produce. My goal for this series is to periodically offer some thematic discussion of that work, highlighting recent analysis by Research staff and adding my own observations on the issue at hand. In this inaugural post, I’ll focus on perhaps the hottest topic going: How artificial intelligence is changing the labor market and hiring behaviors.

• 1.Iceland Belongs in the Eurozone

  In evaluating the trade-offs of joining the European Union and giving up their own currency, Icelanders must recognize that the costs of eurozone membership are smaller than what past data suggest. If anything, being within the eurosystem would make a repeat of Iceland's post-2008 banking crisis exceedingly unlikely.

• 2.Zhu Rongji’s Legacy of Demographic Decline

  Former Chinese Premier Zhu Rongji’s recent death elicited widespread accolades for his role in pushing the market-oriented reforms that unleashed decades of economic growth. But Zhu also oversaw two major policy shifts that have had dire implications for China’s demographic outlook.

• 3.The Global Land Agenda’s Moment of Truth

  As delegates gather this week in Ulaanbaatar, Mongolia, for the 17th Conference of the Parties (COP17) to the UN Convention to Combat Desertification, momentum is building toward a more ambitious global response to land degradation. In fact, there are five promising signs that this time could be different.

• 4.How Trump Is Reinvigorating Democracy

  After a year of commentators lamenting the extent to which Donald Trump had emboldened the world’s autocrats, the political tables may have begun to turn. Not only is Trump deeply unpopular globally, but any government that gets into bed with him is effectively offering proof of its own corruption.

• 5.Ebola is Back-and the IMF’s Relief Fund Is Empty

  Once again, the International Monetary Fund finds itself begging for resources to support poor countries facing a public-health emergency. It is an old problem, but one for which there is a remarkably simple solution.

• 1.The bulk-managed Wi-Fi threat didn’t die – it fragmented (Analyst Angle)

  The FCC’s retreat on bulk billing did not end the fight; it fragmented it. States and cities are now squeezing bulk Wi-Fi economics through opt-outs, access mandates, markup caps and…

• 2.Indosat, Nvidia launch AI center as telco expands AI infra

  The UGM Indosat Nvidia AI Technology Center (NVAITC), launched in Yogyakarta, is part of the Indonesia AI Center of Excellence (AI CoE) initiative In sum – what to know: AI…

• 3.Lockheed’s NetSense turns Verizon’s 5G network into a drone-tracking system

  NetSense demo in Miami tracked drones with unmodified 5G radios In sum – what we know: Lockheed Martin, Verizon, and Nvidia — along with Keysight Technologies, ODC, and Astris AI…

• 4.Criss-cross comms – Lumen bets on east-west AI, while the edge keeps north-south in play

  Lumen sees the biggest AI networking opportunity between data centers and AI factories, but admits inference will also spread to the edge, leaving the future balance between east-west and north-south…

• 5.Fighting talk (and team spirit) – Celona preps private 5G/Wi-Fi for AI scramble in Industry 4.0

  Celona chief Rajeev Shah tells RCR that its new converged two-fer private 5G/Wi-Fi solution, propped up on agentic AI, properly opens the door for physical AI in Industry 4.0 –…

• 1.Source Error

  Check Feed

• 1.An HFM-Inspired Random Access Preamble Design for NTN under High Doppler

  Non-terrestrial networks (NTNs) are a key enabler of ubiquitous 6G connectivity, but the high orbital velocity and long propagation distances in low-Earth orbit (LEO) NTN operation introduce large Doppler shifts and substantial delay uncertainty that challenge New Radio (NR) physical random access channel (PRACH) design. Conventional Zadoff Chu (ZC) and linear frequency modulated (LFM) preambles are particularly vulnerable, as Doppler induced ambiguity and delay Doppler coupling degrade timing estimation and preamble identification. This paper proposes a hyperbolic frequency modulation (HFM) inspired PRACH preamble for robust synchronization and reliable identification under uncompensated or unknown Doppler, detected with a conventional matched filter receiver so that the gains reflect the preamble design. A unified delay Doppler ambiguit...

• 2.XAI-Guided Conservative Decentralized Execution for Offline Multi-Agent Network Slicing

  The recent advances toward sixth-generation (6G) and beyond-6G networks have accelerated the need for intelligent resource management mechanisms capable of supporting heterogeneous services under shared infrastructures in network slicing. However, resource allocation in network slicing naturally forms a resource-coupled cooperative optimization problem with competing slice demands. Slices compete for limited resources to minimize individual latencies while coordinating to avoid conflicts and underutilization. Although multi-agent reinforcement learning (MARL) has shown promising performance in such settings, existing online formulations remain costly, unsafe, and difficult to deploy due to their reliance on environmental interactions and communication among agents. In this work, we present explainable artificial intelligence (XAI)-guided ...

• 3.Omni-Photonic Base Station: A Three-Functional-Domain Photonic Architecture for Evolutionary 6G Wireless Infrastructure

  6G mobile communications impose immersive communication demands for higher data rates and massive connectivity, while emerging integrated sensing-computing-intelligence scenarios require base stations to concurrently enhance computing capability, guarantee service latency, and realize sensing. We propose the Omni-Photonic Base Station-a progressive evolutionary architecture that introduces photonic technologies into three functional domains, namely baseband processing, fronthaul transmission, and the RF front-end, and obtains system-level gains through cross-domain co-design. By introducing photonics, Omni-PBS harnesses the inherent physical advantages of ultra-broad bandwidth, ultra-low propagation latency, and native parallelism to transcend the aforementioned electronic bottlenecks and fulfill the compound demands of 6G scenarios. The ...

• 4.Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks

  6G networks will not be serving as communication infrastructures only; rather, they are expected to evolve into intelligent systems, where thousands of autonomous artificial intelligence (AI) agents are interconnected. The agents are deployed across a wide range of platforms including low Earth orbit (LEO) satellites, high-altitude platforms (HAPs), unmanned aerial vehicles (UAVs), edge servers, and terrestrial devices. These agents continuously observe their environment and exchange information. Semantic communication provides an efficient mechanism for exchanging meaningful information instead of raw data. However, its effectiveness depends on the communicating agents having sufficiently aligned beliefs to correctly interpret and decode the transmitted messages. This assumption becomes difficult to satisfy in the 6G network where hetero...

• 5.Pareto-Aware Hierarchical Reinforcement Learning for Online Resource Allocation in RIS-assisted Large-Scale IoT Systems

  With the rapid evolution of 5G and emerging 6G networks, reconfigurable intelligent surfaces (RIS) have become a critical technology for enhancing wireless communication scenarios. However, optimizing RIS-assisted multi-user systems typically introduces high-dimensional physical layer variables and non-convex Pareto-optimal rate sets, posing severe computational challenges for real-time applications. To address these limitations, this paper proposes a dimension-reduced, hierarchical reinforcement learning (RL) framework, termed Pareto-aware autoencoder-assisted RL (PAAERL), to optimize online resource allocation in RIS-assisted Internet of Things (IoT) networks. Our approach first substitutes high-dimensional continuous RIS beamforming variables with lower-dimensional weight vectors that strictly represent the Pareto-optimal frontier, the...

• 1.No new articles

  Summary available at source link.

• 1.Dependence-Informed Sparse Neural Architecture for Stock Return Prediction

  Using neural networks for stock return prediction typically requires choices about depth and hidden-layer width that are difficult to connect to financial interpretation. We study an alternative: estimate dependence among firm characteristics with a Maximally Filtered Clique Forest (MFCF), then map its clique structure to a Homological Neural Network (HNN). The MFCF maximum clique size K is the only parameter controlling architectural complexity, and it has a clear graphical meaning: it bounds the number of characteristics in each maximal clique and hence the highest interaction order the network can represent. The filtered graph then fixes the neural network's depth, layer widths, and sparse connections before training, in place of a separately chosen depth and width sequence. We apply two HNN variants to annual out-of-sample forecasts o...

• 2.Buy the Rumor, Sell the News: When Is News Priced In?

  Two old market sayings hold that news is already priced in by the time it is published, and that the rumor is bought while the news is sold. Both place the price move associated with a piece of news before and at publication rather than after it. Whether the claims hold, for which kinds of news, and by how much are basic questions about how fast markets absorb public information. We test them on 4.57 million financial news articles covering roughly 3,000 US stocks (2023-2026). A large language model teacher, distilled into a compact classifier through active learning, assigns each article one of 17 event tags and five attributes; articles are clustered into stories to separate first reports from follow-up coverage; and beta-adjusted abnormal returns are measured around the resulting 1.68 million stock-day events, with 364,405 neutral-sent...

• 3.Systemic Risk in Financial Networks Revisited: Debt Dilution as a Backdoor Bail-in

  We develop a model of interbank networks with random liquidity shocks. Networks of dilutable debt---e.g., long-term, unsecured---facilitate efficient liquidity transfers: Shocked banks pledge interbank claims as collateral for new senior debt, diluting existing debt. Unlike with non-dilutable debt, indebtedness and connectedness are sources of stability, not fragility. Dilution is thus a ``backdoor bail-in'' that reallocates losses absent a resolution authority, trigger security, or ex post renegotiation. We uncover a class of networks, ``exponential networks,'' that implement optimal contingent transfers via plain debt. Yet exponential networks are not pairwise stable, whereas some core--periphery networks are, rationalizing observed interbank structures and their under-insurance against crises.

• 4.The Price of Permission: Classification Uncertainty in Constrained Capital Markets

  Shariah-compliant equity screening provides a transparent setting in which institutional rules determine who may own a stock. A binary label identifies current eligibility but not whether the feasible investor base is fragmented across standards or close to changing. We define this instability as classification uncertainty and formalize its investor-base consequence through permitted investor mass. In a 1999-2024 CRSP-Compustat panel of 13,188 securities classified under seven researcher-emulated Shariah rulebooks, screening-rule disagreement and proximity to active boundaries rank next-month screen-implied transitions. U.S. Fama-MacBeth diagnostics do not support an unconditional equal-weighted permission premium, and a September 2023 DJIM/S&P methodology change produces no robust matched repricing. The central event evidence uses 25...

• 5.What Makes a Peer? Valuation-Anchored Similarity in Private Markets

  As more investors contemplate private markets and contend with limited transparency, sparse disclosures, and infrequent transactions, identifying economically meaningful peer companies for comparison is a fundamental challenge for valuation, due diligence, portfolio construction, and risk management. We propose an ensemble tree-based supervised similarity learning framework that defines company similarity through the lens of market valuation rather than static feature matching or semantic descriptions. Specifically, we train a CatBoost gradient-boosted decision tree model on observed private company valuations and derive a valuation-aware similarity metric from importance-weighted leaf-node co-occurrences across the ensemble. The similarity metric captures shared valuation drivers while accommodating nonlinear relationships, mixed data ty...

• 1.An HFM-Inspired Random Access Preamble Design for NTN under High Doppler

  Non-terrestrial networks (NTNs) are a key enabler of ubiquitous 6G connectivity, but the high orbital velocity and long propagation distances in low-Earth orbit (LEO) NTN operation introduce large Doppler shifts and substantial delay uncertainty that challenge New Radio (NR) physical random access channel (PRACH) design. Conventional Zadoff Chu (ZC) and linear frequency modulated (LFM) preambles are particularly vulnerable, as Doppler induced ambiguity and delay Doppler coupling degrade timing estimation and preamble identification. This paper proposes a hyperbolic frequency modulation (HFM) inspired PRACH preamble for robust synchronization and reliable identification under uncompensated or unknown Doppler, detected with a conventional matched filter receiver so that the gains reflect the preamble design. A unified delay Doppler ambiguit...

• 2.XAI-Guided Conservative Decentralized Execution for Offline Multi-Agent Network Slicing

  Summary available at source link.

• 3.Omni-Photonic Base Station: A Three-Functional-Domain Photonic Architecture for Evolutionary 6G Wireless Infrastructure

  6G mobile communications impose immersive communication demands for higher data rates and massive connectivity, while emerging integrated sensing-computing-intelligence scenarios require base stations to concurrently enhance computing capability, guarantee service latency, and realize sensing. We propose the Omni-Photonic Base Station-a progressive evolutionary architecture that introduces photonic technologies into three functional domains, namely baseband processing, fronthaul transmission, and the RF front-end, and obtains system-level gains through cross-domain co-design. By introducing photonics, Omni-PBS harnesses the inherent physical advantages of ultra-broad bandwidth, ultra-low propagation latency, and native parallelism to transcend the aforementioned electronic bottlenecks and fulfill the compound demands of 6G scenarios. The ...

• 4.Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks

  6G networks will not be serving as communication infrastructures only; rather, they are expected to evolve into intelligent systems, where thousands of autonomous artificial intelligence (AI) agents are interconnected. The agents are deployed across a wide range of platforms including low Earth orbit (LEO) satellites, high-altitude platforms (HAPs), unmanned aerial vehicles (UAVs), edge servers, and terrestrial devices. These agents continuously observe their environment and exchange information. Semantic communication provides an efficient mechanism for exchanging meaningful information instead of raw data. However, its effectiveness depends on the communicating agents having sufficiently aligned beliefs to correctly interpret and decode the transmitted messages. This assumption becomes difficult to satisfy in the 6G network where hetero...

• 5.Pareto-Aware Hierarchical Reinforcement Learning for Online Resource Allocation in RIS-assisted Large-Scale IoT Systems

  With the rapid evolution of 5G and emerging 6G networks, reconfigurable intelligent surfaces (RIS) have become a critical technology for enhancing wireless communication scenarios. However, optimizing RIS-assisted multi-user systems typically introduces high-dimensional physical layer variables and non-convex Pareto-optimal rate sets, posing severe computational challenges for real-time applications. To address these limitations, this paper proposes a dimension-reduced, hierarchical reinforcement learning (RL) framework, termed Pareto-aware autoencoder-assisted RL (PAAERL), to optimize online resource allocation in RIS-assisted Internet of Things (IoT) networks. Our approach first substitutes high-dimensional continuous RIS beamforming variables with lower-dimensional weight vectors that strictly represent the Pareto-optimal frontier, the...

• 1.Pareto-Aware Hierarchical Reinforcement Learning for Online Resource Allocation in RIS-assisted Large-Scale IoT Systems

  With the rapid evolution of 5G and emerging 6G networks, reconfigurable intelligent surfaces (RIS) have become a critical technology for enhancing wireless communication scenarios. However, optimizing RIS-assisted multi-user systems typically introduces high-dimensional physical layer variables and non-convex Pareto-optimal rate sets, posing severe computational challenges for real-time applications. To address these limitations, this paper proposes a dimension-reduced, hierarchical reinforcement learning (RL) framework, termed Pareto-aware autoencoder-assisted RL (PAAERL), to optimize online resource allocation in RIS-assisted Internet of Things (IoT) networks. Our approach first substitutes high-dimensional continuous RIS beamforming variables with lower-dimensional weight vectors that strictly represent the Pareto-optimal frontier, the...

• 2.Multi-perspective Imbalance-Conscious 6G Beamforming Optimization and Performance

  The study presents a systematic machine learning (ML) study of 6G-IoT beamforming optimization (6GBO) using supervised and unsupervised approaches. We compared the predictive power of network, environmental, device, and vision feature groups for 6GBO. Additionally, it addressed other unsupervised perspectives that can enhance 6GBO, including clustering network scenarios using methods such as K-means, DBSCAN, and hierarchical clustering. Several imbalance-aware experiments revealed that network features possess better prediction power than device, environmental, and vision feature groups, as evidenced by their recall, F1-score and ROC-AUC values. For unsupervised ML exploration (assessed using Elbow, Silhouette score, and Davies-Bouldin Index methods), the results indicate that the deployment environment and type of device primarily influe...

• 3.Digital Twin Satellite Networks: A Paradigm for Intelligent, Efficient, and Resilient Operations

  Satellite mega-constellations in Low Earth Orbit (LEO) are becoming an important part of next-generation non-terrestrial networks, but their operation remains challenging because of fast network topology variation, intermittent inter-satellite links, hardware disturbances, and strict Size, Weight, and Power (SWaP) constraints. Existing approaches based on Digital Twin (DT), Digital Twin Network (DTN), Software-Defined Networking (SDN), and Open Radio Access Network (O-RAN) provide useful building blocks for intelligent satellite networking, but they do not fully support real-time, predictive, and platform-aware network operation. In this paper, we propose a Digital Twin Satellite Network (DTSN) framework as a closed-loop architecture for reliable and intelligent management of LEO satellite constellations. The proposed framework connects t...

• 4.Integrated Sensing and Communication in 3GPP: Evolution from 5G-Advanced to 6G

  Integrated sensing and communication (ISAC) extends mobile networks from information transfer toward perception of passive objects and environments. By exploiting propagation delay, Doppler, angle, and temporal variation, a mobile network can support detection and tracking while reusing licensed spectrum, infrastructure, and edge computing at network scale and under operator control. Unlike conventional radar, ISAC must additionally address multi-application access, heterogeneous sensing entities, uncertainty, privacy, trust, and integration with communication services. This article reviews the evolution of ISAC in 3GPP from 5G-Advanced to 6G. It explains Release-19 ISAC service requirements and channel models, the Release-20 sensing function architecture and reporting abstractions, and the 5G monostatic baseline for drone detection and t...

• 5.Conversational Orchestration for Organic 6G

  The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its promise, service provisioning that is simple to operate, scalable across independently administered domains, and agile under domain churn (i.e., domains dynamically joining and leaving). Despite advances in cross-domain orchestration, many proposals rely on heavy integration fabrics, multi-layer coordinators, and deep telemetry pipelines that hinder deployability and amplify coordination overhead. We propose a lightweight, decentralized conversational orchestration framework based on Large Language Model (LLM)-driven domain agents. Each domain remains autonomous: an agent observes local state via tools, reasons in a closed loop, and exchanges summaries with neighboring agents over an Agent-to-A...