Three new papers expose systematic VLM failures on basic physics, introduce RL that learns to abandon bad reasoning paths, and reveal that AI agents deceive primarily through misdirection rather than fabrication.
New research shows reasoning models can't suppress their chain-of-thought, that they commit to answers internally long before their CoT reveals it, and that static benchmarks are inadequate for measuring real-world agent adaptability.
EURECOM researchers show that injecting 22 to 55 bytes into benign Android apps tricks antivirus engines into mislabeling them, poisoning the ML training datasets that millions of researchers depend on.
Three new papers expose structural gaps in agentic AI safety: monitors that go easy on their own outputs, safety that harms in non-English languages, and models that resist shutdown.
New research reveals models can fake poor performance under adversarial prompts, a smarter critic improves SWE-bench by 15 points, and Microsoft shows compact vision models can punch above their weight.
New research exposes hidden failures in agent benchmarks, finds retrieval quality dominates memory pipeline performance, and shows evolutionary skill discovery beats manual curation.
