STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents
Large language model (LLM) agents can self-evolve at test time by accumulating experience: retrieving relevant memories before acting and writing new lessons back afterwards. Yet most are single-level: trajectories, distilled workflows and reasoning items all land in one undifferentiated pool indexed by embedding simil...
Guan-Hua Zhu, Han Li, Zhi Wei et al.
· 0 citations