The paper introduces Multiscale Policy Optimization (MPO) for long‑horizon large language model agents, addressing the mismatch between turn‑level critic values and token‑level action generation. MPO combines Multiscale Advantage Estimation (MAE) with turn‑level importance sampling to better align credit assignment and policy updates at the turn scale. Experiments on search, tool‑use, and automation tasks with 4B and 30B‑A3B models show consistent improvements over strong reinforcement learning baselines.
By Tao Ren, Hui Yang, Jia Deng, Tingyang Chen, Qiyao Wang, Shuo Tang, Ziyang Zeng, Yuhua Jiang, Guanghao Li, Huatong Song, Yining Li, Yifan Luo, Kunbao Ding, Feng Chang, Chuan Hao, Ran Tao, Bryan Dai, Jiafeng Liang, Jinyang Jiang
The paper introduces CrEST, a hierarchical credit assignment framework for multi-turn, multi-step large language model agents. CrEST anchors each token’s advantage sign to verifier-defined rewards while using a self-teacher to provide dense magnitude signals, addressing both inter-turn dilution and intra-turn token contribution issues. Experiments on BFCL V3 and WildToolBench show CrEST consistently outperforms reinforcement learning and distillation baselines, especially on long trajectories and strict session-level metrics.
By Zechuan Wang, Siyuan Lu, Hongxuan Zhang, Linjian Mo, Chenyi Zhuang, Leilei Gan
Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over t...
Group-Graph Policy Optimization (G2PO) is a novel group-based reinforcement learning algorithm designed for long-horizon agentic tasks. It transforms linear interaction trajectories into a global state‑transition graph, aggregates identical observations across trajectories to reduce sampling variance, and redefines actions as transitions between state nodes. By employing an edge‑centric advantage estimation and globally standardizing TD errors, G2PO identifies and prioritizes critical transitions, achieving up to 22.2% higher success rates than state‑of‑the‑art baselines on benchmarks such as WebShop, ALFWorld, and AppWorld.
By Yunan Wang, Minghui Song, Zihan Zhang, Shaohan Huang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
The paper introduces Effect-Marginal Policy Optimization (EMPO), a method that addresses credit-update misalignment in multi-turn reinforcement learning for large language model agents. EMPO aligns policy updates with execution-level equivalence by using an effect-level surrogate that couples updates across different textual responses that produce the same effect. Experiments on ALFWorld, WebShop, and Sokoban demonstrate that EMPO improves both task performance and learning efficiency compared to strong baselines.
By Shaojin Ma, Ruitao Wang, Pengyi Li, Jie Yang, Liangyu Chen, Gangyi Zhao, Hongyao Tang, Yan Zheng, Jianye Hao
The paper introduces Potential-Guided Policy Optimization (PGPO), a method for multi-turn agentic tasks that improves credit assignment by estimating empirical state potentials from anchor-state-group return statistics. PGPO derives action advantages from potential differences between adjacent states, enabling cross-trajectory credit propagation and finer-grained step-level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong performance compared to recent group-based reinforcement learning methods, with negligible training overhead.
By Yuyao Zheng, Haipeng Sun, Junwei Bao, Lemao Liu, Hongfei Jiang, Yang Song, Dejing Dou
PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks proposes a new reinforcement learning approach that estimates empirical state potentials from anchor-state-group return statistics within each rollout group. By deriving action advantages from potential differences between adjacent states, PGPO enables cross‑trajectory credit propagation, providing finer‑grained step‑level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong overall performance compared to recent group‑based RL methods, with negligible training overhead.
arXiv:2610.08402v1 Announce Type: new
Abstract: Multi-turn LLM agents often receive sparse task feedback across several interactions, while generating each response token by token. This creates two r...
By Jiaju Chen, Min Yang, Jinghua Piao, Xiaochong Lan, Xu Xia, Xiangnan He, Yong Li
The paper introduces Influence-Aware Policy Optimization (IAPO), a method that models multi‑turn agent rollouts as typed influence‑dependency graphs to better assign credit to actions based on how information and errors flow through user and tool interactions. IAPO transforms the structure of support and failure usage into routing weights that redistribute trajectory‑level advantage, enabling more effective learning from sparse final rewards. Experiments with Qwen3‑4B and Qwen3‑8B on three service‑agent benchmarks show that IAPO outperforms existing multi‑turn reinforcement learning baselines without harming function‑calling performance.
By Bo Ren, Yirong Mao, Yi Yang, Wenhui Que
Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (e.g., GRPO) suffer from a fundamental uniform cr...
Group-based reinforcement learning (RL) methods, such as GRPO and its variants, have become a leading paradigm for training reasoning and agentic large language models (LLMs). While their group-normal...
arXiv:2606. 12384v1 Announce Type: cross Abstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents.
By Xucong Wang, Ziyu Ma, Yong Wang, Yuxiang Ji, Shidong Yang, Guanhua Chen, Pengkun Wang, Xiangxiang Chu