Metraipolis › archive › dc_00da909dceda

DynaFlow: Learning Free-Form Multi-Agent Orchestration — arXiv:2610.34467

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.34467
License (as archived)
CC0-1.0
Archived
2026-10-27T07:55:18.812Z
SHA-256 of the archived text
176fbf24ecc1dfd6c889baa72c2c21625071bbd29a732b08fd475e988b846a55
Stable URL of this page
https://metraipolis.com/documento/dc_00da909dceda

How to cite

DynaFlow: Learning Free-Form Multi-Agent Orchestration — arXiv:2610.34467 — arXiv (en), https://arxiv.org/abs/2610.34467 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00da909dceda (Metraipolis archive dc_00da909dceda, sha256 176fbf24ecc1dfd6c889baa72c2c21625071bbd29a732b08fd475e988b846a55)
BibTeX
@misc{dc00da909dceda,
  title = {DynaFlow: Learning Free-Form Multi-Agent Orchestration — arXiv:2610.34467},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.34467},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00da909dceda; sha256 176fbf24ecc1dfd6c889baa72c2c21625071bbd29a732b08fd475e988b846a55},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34467. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements. We introduce DynaFlow, a framework that integrates free-form executable workflow synthesis into the action space of the main agent. The agent decides when collaboration is needed and generates task-specific programs that coordinate sub-agents through sequential or parallel execution, structured information exchange, and verification. Execution results and traces inform subsequent actions, enabling the agent to adapt collaboration as reasoning progresses. We train only the main agent through supervised fine-tuning on distilled trajectories, followed by refinement on examples filtered for unsupported premises, biased verification, and information-flow defects. All sub-agents remain fixed, separating orchestration learning from executor capability improvement. Across six benchmarks spanning mathematical reasoning, scientific question answering, and multi-hop retrieval, DynaFlow achieves 88.08% overall accuracy in Forced mode, outperforming the strongest evaluated baseline by 10.90 percentage points with the same Qwen3.5-27B backbone. Workflow analysis finds more explicit use, verification, and refinement of upstream outputs after training, highlighting cross-stage information flow as a key dimension of multi-agent orchestration.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.34467 — 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 2026-10-27T07:55:15.041Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).