12 posts published in the last hour 09:37Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment 09:36MemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository Histories 09:36When Health Assistants Agree Too Readily: A Benchmark of…
Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
arXiv:2610.27548v2 Announce Type: new Abstract: When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user…
MemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository Histories
arXiv:2610.27524v1 Announce Type: new Abstract: Code agents increasingly work on evolving real repositories, and memory systems aim to help them reuse…
When Health Assistants Agree Too Readily: A Benchmark of Time-Critical Self-Diagnosis
arXiv:2610.27518v1 Announce Type: new Abstract: Every day, more than 40 million people ask ChatGPT a health question, such as whether laptop posture…
Automated Multi-Agent Organization Design: From Architecture Search to Organizational Learning
arXiv:2610.27531v1 Announce Type: new Abstract: Agentic system design is increasingly shifting from hand-crafted prompts and workflows toward automated…
AI’s hidden storage bill: What inference leaves behind
Ask most executives to picture the cost of AI and they’ll likely see GPUs—racks of accelerators with gigawatts of power—and a waitlist for silicon. But…
Structured-Token Attention for Fine-Grained mmWave Liquid Identification
arXiv:2610.27512v1 Announce Type: new Abstract: Fine-grained liquid identification requires a classifier to distinguish similar substances from compact…
Runtime Control for AI Agents: Closing the Evaluation–Execution Gap in Operational Workflows
arXiv:2610.27480v1 Announce Type: new Abstract: Language-model agents increasingly participate in operational workflows where approvals, binds, and…
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation
arXiv:2610.27450v1 Announce Type: new Abstract: On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of…
Securing Agentic Commerce Through Behavior-Aware Fraud Detection and Cybersecurity for Trusted AI-Agent Payment Authorization
arXiv:2610.27483v1 Announce Type: new Abstract: The growing use of autonomous artificial intelligence agents in digital commerce creates new security…
The More the Better? A Comparison of Single- and Multi-Agent LLM Setups on a Financial Review Task
arXiv:2610.27488v1 Announce Type: new Abstract: Practitioner guidance holds that a large language model reviews a document better when the work is divided…
Anthropic takes on Grok Bot, Meta’s Muse, and OpenAI’s Dots with its always-on agent “Claude Duet”
Anthropic has launched Claude Duet, a proactive AI agent that handles tasks on its own, even when the user is offline. The app is built on Claude Opus 5.5…
Recoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-Improvement
arXiv:2610.27465v1 Announce Type: new Abstract: Agent platforms are starting to improve their own agents: they read a deployed agent’s execution traces,…
AI News Brief Hourly Summary 2026-10-22 11h : 15 posts
15 posts published in the last hour 08:35KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses 08:35Unified Sharp Bounds on Probabilities of Causation 08:34ProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory Perceptions 08:34More Memory, Worse Agents: Error Reproduction…
KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses
arXiv:2610.27417v1 Announce Type: new Abstract: A failed gaming trajectory reveals that an agent needs intervention, but not necessarily how its execution…
Unified Sharp Bounds on Probabilities of Causation
arXiv:2610.27398v1 Announce Type: new Abstract: Probabilities of causation (PoCs) have developed steadily, from the binary measures first introduced by…
ProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory Perceptions
arXiv:2610.27400v1 Announce Type: new Abstract: Large language model (LLM) agents are moving beyond reactive responses toward proactive assistance that…
More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
arXiv:2610.27406v1 Announce Type: new Abstract: LLM agents can improve across tasks without updating model parameters by storing experience from their own…