arXiv:2610.27603v1 Announce Type: new Abstract: Empathetic interaction involves two distinguishable capacities: representing another person’s emotional…
AI News Brief Hourly Summary 2026-10-21 12h : 12 posts
12 posts published in the last hour 09:36The Show-Up Attack: When Subagents Win Over Their Supervisor 09:35Automated Multi-Agent Organization Design: From Architecture Search to Organizational Learning 09:35Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment 09:35RaspAssistant as…
The Show-Up Attack: When Subagents Win Over Their Supervisor
arXiv:2610.27574v1 Announce Type: new Abstract: Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents.…
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…
Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment
arXiv:2610.27548v1 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…
RaspAssistant as an Agentic Framework for Automating Adsorption Simulation Research in Porous Materials
arXiv:2610.27572v1 Announce Type: new Abstract: Porous-material adsorption studies require coordinated structure preparation, force-field selection,…
When LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects
arXiv:2610.27573v1 Announce Type: new Abstract: Large language models (LLMs) can influence user trust and decision-making through subtle linguistic cues,…
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…
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…
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…
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…
Claude Science tackles deadly scorpion stings by designing protein binders from scratch
Anthropic’s Claude independently designed protein binders targeting deadly scorpion neurotoxins. Out of more than 318,000 designs, 211 were tested in the…
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…
AI News Brief Hourly Summary 2026-10-21 11h : 12 posts
12 posts published in the last hour 08:34KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses 08:34Ask to Distill: Learning to Synthesize Data for On-Policy Distillation 08:34Recoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-Improvement 08:33Runtime Control for…
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…
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…
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,…
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…