Metraipolis › archive › dc_4eaf3ce3dfd6

EvoMCP: Co-evolving MCP agents and training data — arXiv:2610.41479

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41479
License (as archived): CC0-1.0
Archived: 2026-11-03T05:23:58.919Z
SHA-256 of the archived text: d02b24647db95085697bb5c00571fcd3d2d1bbede3e5a9aaf3aa6524f612b7b4
Stable URL of this page: https://metraipolis.com/documento/dc_4eaf3ce3dfd6

How to cite

EvoMCP: Co-evolving MCP agents and training data — arXiv:2610.41479 — arXiv (en), https://arxiv.org/abs/2610.41479 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4eaf3ce3dfd6 (Metraipolis archive dc_4eaf3ce3dfd6, sha256 d02b24647db95085697bb5c00571fcd3d2d1bbede3e5a9aaf3aa6524f612b7b4)

BibTeX

@misc{dc4eaf3ce3dfd6,
  title = {EvoMCP: Co-evolving MCP agents and training data — arXiv:2610.41479},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41479},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4eaf3ce3dfd6; sha256 d02b24647db95085697bb5c00571fcd3d2d1bbede3e5a9aaf3aa6524f612b7b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41479. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Supervised fine-tuning of Model Context Protocol (MCP) agents is typically conducted on a static data distribution, which fails to adapt to the student's evolving capabilities and leaves newly exposed weaknesses insufficiently addressed. To address these challenges, we propose \method, an agent--data mutual evolution framework that enables MCP agents to improve through a closed loop of task evolution, trajectory evolution, and supervised fine-tuning. Specifically, \method\ assesses the student's established capabilities and capability gaps from rollout feedback to identify learning targets. Task evolution then translates these targets into executable tasks by adapting the instructions and observable environment states of compatible verified seed tasks while keeping their verifiers aligned. To provide reliable and efficient demonstrations for these tasks, trajectory evolution uses reusable skills to recover failed teacher rollouts and refine successful ones. The resulting task--trajectory pairs are used to fine-tune the student, while accepted tasks seed subsequent evolution. To close the loop, we re-evaluate the updated student and use its feedback to guide the next round of data evolution. Experiments on Toolathlon, MCPMark, and MCP-Atlas demonstrate consistent improvements over the initial student, yielding absolute gains of 16.5\%, 10.2\%, and 12.6\%, respectively. Project page: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41479 — 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 2026-11-03T05:18:52.124Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).