Trajectory-Informed Memory Generation for Self-Improving Agent Systems
arXiv 2603.10600·high signal
Automatically extracts actionable learnings from agent execution traces and stores them for retrieval on future similar tasks, directly addressing agent amnesia where systems repeat identical mistakes across sessions. Decomposes trajectory value into sub-goal components and uses contextual retrieval to surface relevant past experience at inference time, improving success rates on repeated task categories without retraining.