Preprint
Oct 2026
CoMem: Learning to Anticipate Failures from Retrieved Experience
Reflection lets LLM agents improve from their own attempts, but the memory it builds is local to a single task, so an agent reflecting on its own tends to revisit the same explanation for failure. Cross-task reflective memory addresses this in two forms: retrieved memory keeps past experience explicit and looks up rela...
Yu-Liang Shen, Ming Shen, Tian-Jun Yao
· 0 citations