New paper: why agent evaluation is broken
The core argument: evaluation was designed for static models. Agents break every assumption. An agent that succeeds once but fails intermittently is…
New paper: Most LLM agents will collude when given the chance — but many are all talk
“Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems” (arxiv.org/abs/2602.15198) dropped last week. It’s an ICML submission from UMass…
New paper: Your security rules are just prompts, and prompts fail 52% of the time
“Policy Compiler for Secure Agentic Systems” (UW-Madison, Langroid) builds something I have been thinking about since the Moltbook security…
"Safety is not compositional" — an embodied AI paper that explains the defamation agent
New paper: “What Breaks Embodied AI Security” (arxiv.org/abs/2602.17345). It’s about robots and vehicles, not software agents. But its four insights…
New paper: AGENTS.md files actually make coding agents worse at their jobs
A new paper from ETH Zurich just dropped: “Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?”…