Skip to main navigation Skip to search Skip to main content

Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation

  • Zihao Cheng
  • , Zeming Liu*
  • , Yingyu Shan
  • , Xinyi Wang
  • , Xiangrong Zhu
  • , Yunpu Ma
  • , Hongru Wang
  • , Yuhang Guo
  • , Wei Lin
  • , Yunhong Wang
  • *Corresponding author for this work
  • Beihang University
  • Beijing Institute of Technology
  • Ludwig Maximilian University of Munich
  • Munich Center for Machine Learning
  • University of Edinburgh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

While large language model-powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert agents), existing frameworks typically treat these two evolutionary processes in isolation. This separation overlooks their intrinsic interdependence: the former is inherently bounded by a manually predefined static toolset, while the latter generates new assets from scratch without experiential guidance, leading to limited capability growth and unstable evolution. To address this limitation, we introduce a novel paradigm of co-evolutionary Capability Expansion and Experience Distillation. Guided by this paradigm, we propose the Mem2Evolve, which integrates two core components: Experience Memory and Asset Memory. Specifically, Mem2Evolve leverages accumulated experience to guide the dynamic creation of assets, thereby expanding the agent's capability space while simultaneously acquiring new experience to achieve co-evolution. Extensive experiments across 6 task categories and 8 benchmarks demonstrate that Mem2Evolve achieves improvement of 18.53% over standard LLMs, 11.80% over agents evolving solely through experience, and 6.46% over those evolving solely through asset creation, establishing it as a substantially more effective and stable self-evolving agent framework. Code is available at: https://buaa-irip-llm.github.io/Mem2Evolve.

Original languageEnglish
Title of host publicationLong Papers
EditorsMaria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
PublisherAssociation for Computational Linguistics (ACL)
Pages20784-20831
Number of pages48
ISBN (Electronic)9798891763906
DOIs
Publication statusPublished - 2026
Event64th Annual Meeting of the Association for Computational Linguistics, ACL 2026 - San Diego, United States
Duration: 2 Jul 2026 → 7 Jul 2026

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference64th Annual Meeting of the Association for Computational Linguistics, ACL 2026
Country/TerritoryUnited States
CitySan Diego
Period2/07/26 → 7/07/26

Fingerprint

Dive into the research topics of 'Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation'. Together they form a unique fingerprint.

Cite this