Metraipolis › archive › dc_02c59603880e
EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems — arXiv:2610.34450
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34450
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:51:32.128Z
- SHA-256 of the archived text
ffeccacc3b8149d39d9d5d0d1efe2b52f3d54e92ea90276c58f52e6b7ffb9f8e- Stable URL of this page
https://metraipolis.com/documento/dc_02c59603880e
How to cite
EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems — arXiv:2610.34450 — arXiv (en), https://arxiv.org/abs/2610.34450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02c59603880e (Metraipolis archive dc_02c59603880e, sha256 ffeccacc3b8149d39d9d5d0d1efe2b52f3d54e92ea90276c58f52e6b7ffb9f8e)
BibTeX
@misc{dc02c59603880e,
title = {EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems — arXiv:2610.34450},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34450},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02c59603880e; sha256 ffeccacc3b8149d39d9d5d0d1efe2b52f3d54e92ea90276c58f52e6b7ffb9f8e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decentralized multi-agent systems (MAS) enable large language model agents to interact without centralized control. Agents need to adapt to other agents at test time and reuse accumulated experience to refine their interaction strategies for future interactions across cooperative, mixed-motive, and adversarial settings. However, existing approaches often develop adaptation mechanisms for particular interaction settings. This raises a central question: how can decentralized MAS support test-time adaptation and reliable experience reuse across interaction settings? We propose EvolveMAS, a unified self-evolution framework that supports experience-driven adaptation within and across episodes. EvolveMAS pairs each main agent with a dedicated MemoryAgent for test-time memory governance, which maintains isolated Structured Memory outside the main agent's reasoning context. EvolveMAS organizes adaptation into two complementary processes: Within-Episode Online Adaptation and Cross-Episode Knowledge Evolution. During Within-Episode Online Adaptation, MemoryAgent updates episodic, semantic, and working memory from interaction evidence to inform subsequent actions. During Cross-Episode Knowledge Evolution, the main agent uses memory and episode outcomes to distill reusable interaction knowledge comprising partner profiles and interaction strategies for subsequent episodes. Across five benchmarks and six evaluation configurations spanning the three interaction settings, EvolveMAS achieves the highest normalized average score of 77.2 among the compared methods. Ablations show that test-time memory governance and cross-episode knowledge reuse both improve performance. Interaction traces further illustrate how updated memory and distilled knowledge guide subsequent interactions. These results support experience-driven adaptation in decentralized MAS without updating model parameters. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.34450 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T08:51:13.283Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).