EXG: Self-Evolving Agents with Experience Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Yuxin, Zhang, Siyuan, Wang, Hanchen, Qin, Lu, Zhang, Ying, Zhang, Wenjie
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909052899950592
author Jin, Yuxin
Zhang, Siyuan
Wang, Hanchen
Qin, Lu
Zhang, Ying
Zhang, Wenjie
author_facet Jin, Yuxin
Zhang, Siyuan
Wang, Hanchen
Qin, Lu
Zhang, Ying
Zhang, Wenjie
contents Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during execution rarely translating into systematic improvement over time. In response, a growing line of work on self-evolving agents explores how agents can improve through experience during deployment, but most existing approaches either rely on ad hoc reflection limited to single-task correction or adopt unstructured memory that accumulates fragmented experience with delayed usability. To address this limitation, we introduce EXG, an experience graph framework for self-evolving agents that explicitly organizes accumulated successes and failures into a structured, relational representation. EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module. This design also enables EXG to serve as a plug-and-play component for existing self-evolving agents, organizing prior experience into a unified experience graph and improving both solution quality and resource efficiency as deployment progresses. Extensive experiments across code generation and reasoning benchmarks show that EXG attains more favorable performance-efficiency trade-offs than reflection- and memory-based baselines in both online and offline evaluations. Our results suggest that structuring experience as a graph provides a principled foundation for scalable and transferable self-evolving agent behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17721
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EXG: Self-Evolving Agents with Experience Graphs
Jin, Yuxin
Zhang, Siyuan
Wang, Hanchen
Qin, Lu
Zhang, Ying
Zhang, Wenjie
Artificial Intelligence
Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during execution rarely translating into systematic improvement over time. In response, a growing line of work on self-evolving agents explores how agents can improve through experience during deployment, but most existing approaches either rely on ad hoc reflection limited to single-task correction or adopt unstructured memory that accumulates fragmented experience with delayed usability. To address this limitation, we introduce EXG, an experience graph framework for self-evolving agents that explicitly organizes accumulated successes and failures into a structured, relational representation. EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module. This design also enables EXG to serve as a plug-and-play component for existing self-evolving agents, organizing prior experience into a unified experience graph and improving both solution quality and resource efficiency as deployment progresses. Extensive experiments across code generation and reasoning benchmarks show that EXG attains more favorable performance-efficiency trade-offs than reflection- and memory-based baselines in both online and offline evaluations. Our results suggest that structuring experience as a graph provides a principled foundation for scalable and transferable self-evolving agent behavior.
title EXG: Self-Evolving Agents with Experience Graphs
topic Artificial Intelligence
url https://arxiv.org/abs/2605.17721