Metraipolis › archive › dc_2ef6756ba82e
EvoGroup: A Self-Evolving Harness for Group Agents in Shared Contexts — arXiv:2611.03868
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03868
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:42:19.350Z
- SHA-256 of the archived text
b6ac025b922f86feb736c4027b1a987e64c7e66c8e5b5d672b64317b4d68ad57- Stable URL of this page
https://metraipolis.com/documento/dc_2ef6756ba82e
How to cite
EvoGroup: A Self-Evolving Harness for Group Agents in Shared Contexts — arXiv:2611.03868 — arXiv (en), https://arxiv.org/abs/2611.03868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ef6756ba82e (Metraipolis archive dc_2ef6756ba82e, sha256 b6ac025b922f86feb736c4027b1a987e64c7e66c8e5b5d672b64317b4d68ad57)
BibTeX
@misc{dc2ef6756ba82e,
title = {EvoGroup: A Self-Evolving Harness for Group Agents in Shared Contexts — arXiv:2611.03868},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03868},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ef6756ba82e; sha256 b6ac025b922f86feb736c4027b1a987e64c7e66c8e5b5d672b64317b4d68ad57},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
With the rise of Group Agent such as Claude Tag, agents increasingly serve as digital workers for long-term team collaboration. These agents operate over shared contexts that continuously accumulate through multi-user interactions. However, existing agent memory systems are mainly designed for individual users and struggle to capture group-level knowledge in shared contexts, including group relationships and collaboratively formed knowledge. Manual memory strategies further limit adaptation to diverse and evolving shared contexts. To this end, we propose \textbf{EvoGroup (EvoG)}, a self-evolving harness for group agents that starts from a minimal six-tool cold start and adapts through interaction with shared context. EvoG uses confidence and task outcomes to select informative trajectories, while also eliciting self-reflections on uncertainty in low-confidence cases. The analysis agent then examines selected trajectories through adaptive progressive disclosure, followed by bucketed analysis to synthesize high-level findings that guide the evolve agent in revising the Harness. Empirically, pass@1 on held-out split of EverMemBench improves from 71.07\% to 89.58\%, surpassing both self-evolving memory and human-designed harnesses, including Claude Code (85.83\%). To evaluate generalization, we freeze the evolved harness and evaluate it on the unseen GroupMemBench, where, with GPT-5.5, it demonstrates effective generalization and outperforms both memory baselines and human-designed harnesses.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.03868 — 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 2026-11-04T21:36:04.396Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).