arXiv:2610.07521v1 Announce Type: new Abstract: Driving models increasingly ground reasoning in causal relations, spatial structure, perceptual evidence,…
From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models
arXiv:2610.07514v1 Announce Type: new Abstract: A vision-language model may need to combine an image with a prompt to recognize a safety risk that neither…
On Open-Ended Information Seeking for Information Elicitation Agents
arXiv:2610.07509v1 Announce Type: new Abstract: Information elicitation is an open-ended information-seeking problem in which an interaction can unfold in…
A Systematic Investigation of Bias in Large Language Models for Advertising Relevance
arXiv:2610.07544v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to judge how well an advertisement matches a query, but…
Decoupled Multi-Agent Orchestration
arXiv:2610.07556v1 Announce Type: new Abstract: Learned orchestration can automatically construct effective language-model multi-agent systems, but…
PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic Reasoning
arXiv:2610.07473v1 Announce Type: new Abstract: Large language models show promise in clinical reasoning, but psychiatric interviewing requires guiding an…
MARS: Multi-resolution Adaptive Routing for Sequential Recommendation
arXiv:2610.07505v1 Announce Type: new Abstract: Long-history recommenders often compress each user’s history into a compact, candidate-independent memory…
COMPASS: Finding Where Reasoning Lives in Language Models
arXiv:2610.07469v1 Announce Type: new Abstract: Explicitly eliciting reasoning substantially improves LLM performance. Existing approaches require a…
OpenAI dumps 372 AI-generated math proofs on GitHub, telling the academic world to keep up
OpenAI has published 372 AI-generated mathematical results on GitHub, including Lean formalizations for machine verification. Each result consumed about…
In With the Old: Enhancing ‘Classical’ Document Automation with Generative AI
arXiv:2610.07480v1 Announce Type: new Abstract: Software-based legal assistance systems have leveraged many different forms of knowledge representation…
ChatGPT for Teens is an ‘unacceptable risk,’ says Common Sense Media
Common Sense Media, a nonprofit that offers reviews of apps, services, and entertainment with a focus on youth safety, today said that OpenAI’s ChatGPT…
Does Muon Need Fine-Grained Spectral Shaping?
arXiv:2610.07497v1 Announce Type: new Abstract: Muon combines current and past gradients into matrix momentum. For $M=U\Sigma V^\top$, the idealized polar…
AI News Brief Hourly Summary 2026-10-07 11h : 12 posts
12 posts published in the last hour 08:33Auditable Claims about AI Agents 08:332d-fet-bench: from spatial reasoning to fet design on flakes 08:33Adaptive Gait Biofeedback With Participant-Held-Out Modeling and Participant-Specific Updating in Chronic Ankle Instability 08:33Defense-in-Depth for LLMs: Evaluating Memory Gates…
Auditable Claims about AI Agents
arXiv:2610.07459v1 Announce Type: new Abstract: Organizations make claims about their AI agents: a person approves every external email, every action is…
2d-fet-bench: from spatial reasoning to fet design on flakes
arXiv:2610.07423v1 Announce Type: new Abstract: Field-effect transistor (FET) layouts on exfoliated two-dimensional flakes are typically drawn by hand for…
Adaptive Gait Biofeedback With Participant-Held-Out Modeling and Participant-Specific Updating in Chronic Ankle Instability
arXiv:2610.07428v1 Announce Type: new Abstract: Adaptive gait biofeedback may support repeated practice in chronic ankle instability, but its evaluation…
Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy
arXiv:2610.07403v1 Announce Type: new Abstract: Long-term memory allows Large Language Models (LLMs) to maintain personalized context across interactions,…
COSMIC shuts the door on AI code as GNOME debates letting bug reports in
System76 demands human-written contributions, while a rival desktop developer argues bot-found flaws are too valuable to ignore