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
arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.
By Xintong Li, Sha Li, Yuwei Zhang, Changlong Yu, Rongmei Lin, Hongye Jin, Shuyi Guan, Xin Liu, Linwei Li, Qingyu Yin, Jingbo Shang
arXiv:2605. 13217v1 Announce Type: cross Abstract: Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge.
By Siyuan Zhu, Chao Yu, Rongxin Yang, Zongkai Liu, Jinjun Hu, Qiwen Chen, Yibo Zhang
arXiv:2605. 26684v2 Announce Type: replace-cross Abstract: Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agentic tasks.
By Xin Cheng, Shuo He, Lang Feng, HaiYang Xu, Ming Yan, Lei Feng, Bo An
PlanPO introduces a group planning-aware policy optimization method for multi-turn agentic large language models, addressing the issue of advantage collapse caused by treating all successful trajectories equally. By incorporating coarse-to-fine advantage signals that reflect differences in trajectory and turn lengths, PlanPO encourages agents to learn generalizable planning and generation behaviors. Experiments show a 27.2% average improvement over GRPO on benchmarks such as ALFWorld, WebShop, and SciWorld, with minimal extra training cost.
By Dayang Liang, Liyuan He, Xuan Feng, Shuxin Li, Bo An, Yunlong Liu
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...
The paper introduces Reverse‑Turn Policy Optimization (RTPO), a method that restructures multi‑turn agentic reinforcement learning rollouts into sparse reverse trees and updates policies in temporal reverse order. This approach addresses three key instability sources—context mismatch, weak turn‑level credit assignment, and asynchronous policy drift—by aligning each decision with its downstream continuation. Theoretical analysis shows RTPO eliminates context mismatch and drift, reduces credit bias, and converges to recursive optimality, while experiments demonstrate performance gains of 21.50% over trajectory‑level and 10.76% over turn‑level baselines on multi‑turn agentic RL benchmarks.
By Yugu Li, Jimmy Cao, Jianglin Qiao, Siyi Hu
arXiv:2607. 04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks.
By Qiang Liu, Taian Guo, Ruizhi Qiao, Xing Sun
arXiv:2606. 05885v1 Announce Type: new Abstract: Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards.
By Yuanfan Li, Qi Zhou, Wenjing Duan, Lu Chen
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
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:2608. 07371v1 Announce Type: new Abstract: Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards.
By Haoyu Zheng, Yun Zhu, Qing Wang, Wenqiao Zhang