Corrupt Agent Scores, Memory Bottlenecks, Skill Evolution
New research exposes hidden failures in agent benchmarks, finds retrieval quality dominates memory pipeline performance, and shows evolutionary skill discovery beats manual curation.
Memory systems
AI Research Roundup: Agent Behavioral Contracts, Autonomous Memory, and Certified Circuits
Three new papers tackle agent reliability through formal contracts, active knowledge acquisition for memory systems, and provably stable mechanistic interpretability.
