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.
By Yuyang Wu, Yang Liu, Zequn Xie, Junjie Wang, Dan Yang, Zehao Tan, Ding-Chu Zhang, Junming Yang, Yue Shen, Jian Wang, Jinjie Gu
arXiv:2606. 10684v1 Announce Type: cross Abstract: Modern language agents which perform multi-step reasoning have shown strong performance in knowledge-intensive question answering.
By Jaewan Park, Solbee Cho, Jay-Yoon Lee
arXiv:2602. 05965v2 Announce Type: replace-cross Abstract: Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.
By Joseph Fioresi, Parth Parag Kulkarni, Ashmal Vayani, Song Wang, Mubarak Shah
Dr.Credit introduces a rubric‑grounded credit assignment method that evaluates intermediate tool turns in deep research agents by comparing the information returned to the history of accepted support for each rubric. Unlike traditional approaches that rely on ground‑truth answers, Dr.Credit uses task requirements as a shared reference, distinguishing new support from previously seen evidence and recognizing partial rubric fulfillment. Experiments on four benchmarks show that Dr.Credit outperforms open deep research baselines across all primary metrics, achieving performance competitive with proprietary models while enabling more efficient evidence acquisition and higher‑quality reports under limited turn budgets.
RubricEM is a unified reinforcement learning framework designed for deep research agents that plan, search, evaluate evidence, and synthesize long‑form reports. It introduces rubric‑guided policy decomposition, combining supervised fine‑tuning to scaffold agents with rubrics, stage‑structured GRPO for fine‑grained credit assignment, and a reflection meta‑policy for experience reuse. The resulting RubricEM‑8B model outperforms larger open models on four long‑form research benchmarks and approaches the performance of proprietary deep‑research systems.
By Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang, Jun Yan, Yanfei Chen, Chun-Liang Li, Long T. Le, Rujun Han, George Lee, Hanghang Tong, Chen-Yu Lee, Tomas Pfister
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
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:2607. 26784v1 Announce Type: new Abstract: Large language model agents often encounter related yet distinct tasks that share reusable solution patterns.
By Zhiyuan Yao, Yuxin Chen, Zhengxi Lu, Zishan Xu, Yueqing Sun, Yifu Guo, Yuquan Lu, Zhengzhou Cai, Kangning Zhang, Zhuowen Han, Zi-Han Wang, Ziang Ye, Qi Gu, Xunliang Cai, Weiwen Liu, Yongliang Shen
The paper introduces DAC (Divide and Cooperate), a role‑decomposed training framework that separates evidence acquisition (searcher) and response generation (generator) in agentic search systems. DAC uses task‑specific external verification signals to provide cross‑verification rewards, allowing the generator to abstain when evidence is insufficient and to assign credit appropriately to each role. Experiments on seven QA benchmarks and two model backbones show that DAC consistently outperforms single‑agent and multi‑agent baselines, with gains attributed to coordinated improvements in both search and generation.
By Jaewan Park, Solbee Cho, Jay-Yoon Lee
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
Large language model agents often encounter related yet distinct tasks that share reusable solution patterns. Yet standard agentic reinforcement learning treats tasks as independent episodes, while existing approaches to skill learning either focus on repeated attempts of one task or use pipelines with multiple stages that entangle extraction, retrieval, and execution.
arXiv:2602. 08335v2 Announce Type: replace Abstract: Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems.
By Yanming Li, Xuelin Zhang, WenJie Lu, Ziye Tang, Maodong Wu, Haotian Luo, Tongtong Wu, Zijie Peng, Hongze Mi, Yibo Feng, Naiqiang Tan, Chao Huang, Lian Peng, Li Shen