arXiv AI By Yuyang Wu, Yang Liu, Zequn Xie, Junjie Wang, Dan Yang, Zehao Tan, Ding-Chu Zhang, Junming Yang, Yue Shen, Jian Wang, Jinjie Gu

From Delegation to Coordination: Learning Efficient Multi-Agent Deep Research

Read the original on arXiv AI →

The paper introduces LEAD-RL, a joint training framework for multi‑agent deep research systems that assigns credit to subagents based on their contribution to the main agent’s research utility. By evaluating each subagent’s report during training and gating the inherited team advantage, LEAD‑RL avoids rewarding misleading subagent outputs and focuses on final‑answer correctness. Experiments on five benchmarks and two model families show that LEAD‑RL improves answer quality, achieving a 2.49‑point accuracy gain on BrowseComp and a 24.5% reduction in critical‑path cost compared to shared‑credit joint training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers
5d ago

From Delegation to Coordination: Learning Efficient Multi-Agent Deep Research

The paper introduces LEAD‑RL, a joint training framework for multi‑agent deep research that uses contribution‑aware credit assignment to improve coordination between a main agent and its subagents. By evaluating each subagent’s report for research utility and gating its team advantage, the method avoids rewarding misleading subagent outputs and focuses on final answer correctness. Experiments on five benchmarks show that LEAD‑RL boosts answer quality, achieving a 2.49‑point accuracy gain on BrowseComp and a 24.5% reduction in critical‑path cost compared to shared‑credit joint training.

arXiv AI
Jun 9

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

arXiv:2603. 21563v4 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding.

By Zhongyi Li, Wan Tian, Yikun Ban, Jinju Chen, Huiming Zhang, Yang Liu, Fuzhen Zhuang
arXiv Computation and Language
Oct 19

MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation

arXiv:2610.23234v1 Announce Type: new Abstract: In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult b...

By Yuhan Sun, Jiaxin Zhao, Yongdong Luo, Yibo Hu, Meiguang Jin, Junfeng Ma, Weixun Wang, Weihang Pan, Zhongan Bi
arXiv AI
Jun 9

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

arXiv:2606. 09730v1 Announce Type: new Abstract: Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite.

By Pu Ning, Quan Chen, Kun Tao, Xinyu Tang, Tianshu Wang, Qianggang Cao, Xinyu Kong, Zujie Wen, Zhiqiang Zhang, Jun Zhou