AI RESEARCH
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents
arXiv CS.CL
•
ArXi:2605.30712v1 Announce Type: new Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction, but they often solve tasks from scratch and fail to reuse successful strategies or failure lessons from prior experience. Fine-tuning on collected experience can improve reuse, but it is inflexible when stronger or suitable executors emerge. We propose ExpGraph, a model-agnostic experience learning framework that enables frozen and replaceable LLM executors to improve through external experience reuse without parameter updates.