Large language model agents share experience to improve task success
XferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents
Multiagent SystemsArtificial Intelligence
Summary
Large language model agents sometimes repeat tasks without getting better at them. The authors introduce XferAgent, a system that helps these agents share their past task experiences with each other in a careful way. This sharing helps agents learn from one another even if they have different backgrounds or ways of working. Tests show that using this system leads to better success on tasks over time as agents reuse and build on shared knowledge.
What this means in practice
- •For ai system developers: Improve collaborative AI agents by enabling them to share and reuse experiences across different designs to boost task performance.
- •For customer support automation teams: Build support chatbots that learn from conversations handled by other bots, improving responses over time even if bots are set up differently.
Authors
Weihao Li, Jun Bai, Shijie Chen, Qincheng Lu, Xinyu Wang, Ziyang Song
Abstract
Large language model (LLM) agents can reuse experience from prior task executions to improve performance on subsequent tasks. Although existing methods enable cross-agent experience sharing, differences in agents' execution histories and task requirements make shared experiences difficult to reuse effectively. We propose XferAgent, a framework for cross-agent experience transfer that organizes reusable experience in local and shared experience graphs. XferAgent reconciles compatible contributions from heterogeneous agents while avoiding unreliable merges. For each new task, it selects shared experiences and integrates them with the target agent's local experience to support task execution. Experiments across diverse task domains show improvements over representative memory-based methods and effective experience transfer between heterogeneous agent frameworks. Cumulative task success also increases over successive task passes as agents update and reuse their experiences.