AgentRM proposes a generalizable reward model to guide LLM-based agents during test-time search, outperforming direct policy fine-tuning. Three reward modeling strategies—explicit, implicit, and LLM-as-a-judge—are explored, and AgentRM improves base policy performance by an average of 8.8 points across nine tasks, surpassing top general agents by 4.0 points. It also shows strong weak-to-strong generalization and can boost specialized agents, with plans to release code for further research.
By Yu Xia, Jingru Fan, Weize Chen, Siyu Yan, Xin Cong, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Maosong Sun
arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.
By Yijun Lu, Rui Ye, Jiajun Wang, Yuwen Du, Tian Jin, Songhua Liu, Siheng Chen
arXiv:2610.17666v1 Announce Type: cross
Abstract: Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps....
By Xuyan Ye, Xiyan Fu, Shengda Fan, Jiawei Cui, Yankai Lin, Wei Lu
arXiv:2606. 00017v1 Announce Type: new Abstract: Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players.
By Aliaksei Korshuk, Alexander Buyantuev, Ilya Makarov
arXiv:2608.01822v2 Announce Type: replace
Abstract: Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search...
By Wentao Tan, Qiong Cao, Jiaqi Wang, Nan Duan
arXiv:2609.36641v1 Announce Type: cross
Abstract: Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning....
By Shengda Fan, Xin Cong, Zhong Zhang, Haotian Chen, Yankai Lin
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
By Wonjoong Kim, Yeonjun In, Sangwu Park, Dongha Lee, Chanyoung Park
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:2607.24162v3 Announce Type: replace
Abstract: Workflow search pays for complete quality observations, whose execution cost changes as reusable prefixes accumulate. AgentUCT uses an economic mod...
By Yang Li, Hai Liu, Dian Shao, Yu Wang, Xiyu Chen, Di Wan, Sergey Volkov, Bozhi Wang, Ziyu Sun, Sihang Liu, Ye Luo, Xiaowei Zhang
arXiv:2602.03053v2 Announce Type: replace
Abstract: Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification,...
By Vishal Venkataramani, Haizhou Shi, Zixuan Ke, Austin Xu, Xiaoxiao He, Yingbo Zhou, Semih Yavuz, Hao Wang, Shafiq Joty
arXiv:2607. 23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning.
By Yang Wan, Zhenhao Zhang, Jierui Wang, Linchao Zhu
arXiv:2607. 09153v1 Announce Type: new Abstract: Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems.
By Peng Kuang, Haibo Jin, Xiaoyu Han, Yanli Wang, Xiaopeng Yuan, Ye Yu, Kaidi Xu, Haohan Wang