GenAI Daily for Practitioners

Executive Summary • Here are the concise, non-sensationalist bullets for enterprise practitioners: • From Model Scaling to System Scaling: Scaling the Harness in Agentic AI: - Scaling AI systems requires a combination of model scaling and system scaling to achieve efficient and effective deployment. (Cost: N/A, Compliance: N/A, Deployment: Requires careful system design) • PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction: - PolyGnosis 2.0 achieves 14.5% improvement in LLM reasoning via agentic harness engineering. (Benchmarks: 14.5% improvement, Cost: N/A, Compliance: N/A, Deployment: Requires LLM integration) • PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation: - PennySynth synthesizes high-quality quantum code with 95.6% accuracy using RAG-driven data synthesis. (Benchmarks: 95.6% accuracy, Cost: N/A, Compliance: N/A, Deployment: Requires quantum computing infrastructure) • CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities: - CITYREP provides a unified benchmark for evaluating urban representations across

Research

• From Model Scaling to System Scaling: Scaling the Harness in Agentic AI \ This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling th… \ Source • arXiv cs.LG • 19:59
• PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction \ This paper introduces PolyGnosis 2.0, a pioneering multi-agent architecture designed to extract predictive intelligence by synthesizing Polymarket anomaly signals with global Open Source Intelligence (OSINT) streams, specifically Global Da… \ Source • arXiv cs.CL • 17:30
• PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation \ The growing complexity of quantum programming frameworks has exposed a critical limitation in existing large language model (LLM)-based code assistants: general-purpose models hallucinate PennyLane-specific gate names, misplace device conf… \ Source • arXiv cs.CL • 10:26
• CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities \ Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundation models. However, current evaluations are limited, typically focusing on one or two … \ Source • arXiv cs.LG • 19:03
• Language Models Need Sleep \ Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in which a model peri… \ Source • arXiv cs.CL • 19:55
• Automated Benchmark Auditing for AI Agents and Large Language Models \ Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete environment specifications, and brittle evaluation logic that huma… \ Source • arXiv cs.CL • 19:44
• Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Service \ Online Terms of Service often function as contracts of adhesion, creating asymmetries that may expose consumers to potentially abusive clauses. In Chile, assessing such clauses is legally challenging because some provisions clearly violate… \ Source • arXiv cs.CL • 18:38
• Forgotten Words: Benchmarking NeoBERT for Dementia Detection in Low-Resource Conversational Filipino and English Speech \ Dementia detection from spontaneous speech offers a scalable approach to cognitive screening, yet NLP systems remain predominantly English-centric. This limitation is especially acute in the Philippines, where Filipino-English code-switchi… \ Source • arXiv cs.CL • 18:26
• Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents \ While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between… \ Source • arXiv cs.CL • 17:47
• TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings \ Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications such as disaster management, traffic planning, embodied navigation, world modeling, and geography ed… \ Source • arXiv cs.CL • 17:45
• TTPrint: Evidence-Grounded TTP Extraction via Diverge-then-Converge Verification \ Extracting MITRE ATT&CK techniques from cyber threat intelligence (CTI) reports is an open-set, multi-label problem requiring both high recall (not missing techniques) and high precision (not hallucinating unsupported ones). Existing m… \ Source • arXiv cs.CL • 15:31
• Judge Circuits \ LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its output format changes (e.g., a 1-5 rating vs. a True/False label). Existing diagnoses o… \ Source • arXiv cs.CL • 14:34

Big Tech

No items today.

Regulation & Standards

No items today.

Enterprise Practice

No items today.

Open-Source Tooling

No items today.

— Personal views, not IBM. No tracking. Curated automatically; links under 24h old.