跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 28 天前AI 評分43

DynaFlow:學習自由形式的多智能體編排

DynaFlow: Learning Free-Form Multi-Agent Orchestration

AI 導讀

DynaFlow 讓主智能體合成可執行工作流程,以協調子智能體進行協作。研究只訓練主智能體,子智能體保持不變;在六項基準測試中,DynaFlow 使用 Qwen3.5-27B 主幹模型,在 Forced mode 達到 88.08% 總體準確率,較最強的受測基線高 10.90 個百分點。

正文

Published on Oct 25

·

Submitted by

Qi Li

on Oct 27

Authors:

,

,

Abstract

DynaFlow enables adaptive multi-agent collaboration by letting a main agent synthesize executable workflows that coordinate sub-agents through structured execution and verification.

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.

View arXiv page View PDF Project page GitHub Add to collection

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.34467 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.34467 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.34467 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co