arXiv:2608.30386v2 Announce Type: replace-cross Abstract: Hybrid linear-attention architectures have recently scaled to large open-weight models, offering…
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
arXiv:2608.06202v2 Announce Type: replace-cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about…
STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
arXiv:2608.09524v2 Announce Type: replace-cross Abstract: Incident response planning is critical for restoring compromised software systems. Existing…
Learning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks
arXiv:2607.22724v2 Announce Type: replace-cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM)…
Medical foundation models converge less under label supervision
arXiv:2607.20274v3 Announce Type: replace-cross Abstract: Diagnostic classifiers and imaging biomarkers are fitted on the embeddings of medical foundation…
Improving Certified Robustness via Adversarial Distillation
arXiv:2606.31653v2 Announce Type: replace-cross Abstract: Certified training aims to produce models whose predictions can be formally verified against…
Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids
arXiv:2607.16004v2 Announce Type: replace-cross Abstract: Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand…
The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
arXiv:2606.27045v2 Announce Type: replace-cross Abstract: AI coding agents dramatically accelerate implementation speed but introduce two structural…
IMF Warns AI Market Correction Could Trigger Global Financial Turmoil
The International Monetary Fund released its October 2026 Global Financial Stability Report on October 13, 2026, warning that weaker or less durable…
The One-Word Census: Answer-Choice Conformity Across 105 Language Models
arXiv:2607.12796v4 Announce Type: replace-cross Abstract: When a language model must choose one answer from a large space of equally valid options, which…
AI News Brief Hourly Summary 2026-10-13 09h : 10 posts
10 posts published in the last hour 06:32Scalable Circuit Learning for Interpreting Large Language Models 06:32Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence 06:32Erased, but Not Gone: Output Forgetting Is Not True Forgetting 06:32RoboMME-Interference: Benchmarking…
Scalable Circuit Learning for Interpreting Large Language Models
arXiv:2606.16939v2 Announce Type: replace-cross Abstract: A prominent research direction in mechanistic interpretability is learning sparse circuits over…
Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence
arXiv:2606.19386v2 Announce Type: replace-cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state – a…
Erased, but Not Gone: Output Forgetting Is Not True Forgetting
arXiv:2606.25001v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy…
RoboMME-Interference: Benchmarking Robot Memory Under Interference
arXiv:2606.22338v4 Announce Type: replace-cross Abstract: Robots deployed in realistic settings will accumulate experience across many sessions and tasks…
Decoupling the Declarative from the Procedural in Vision-Language-Action Models
arXiv:2606.21496v2 Announce Type: replace-cross Abstract: Deploying generalist robotic agents in the real world requires transferable skills.…
PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents
arXiv:2606.16215v2 Announce Type: replace-cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several…
The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
arXiv:2606.05328v2 Announce Type: replace-cross Abstract: Modern video diffusion models generate increasingly realistic and temporally coherent videos,…