Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2510.26270 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911725672988672 |
|---|---|
| author | Yuan, Jiazhen Gong, Zhike Hang, Jinquan Bai, Zhengbiao Zhao, Wei |
| author_facet | Yuan, Jiazhen Gong, Zhike Hang, Jinquan Bai, Zhengbiao Zhao, Wei |
| contents | Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based reinforcement learning is widely adopted, which reinforces trajectories with higher relative performance within the group. However, in most existing methods, every step within a trajectory and every trajectory with the same terminal reward receive identical credit, regardless of their actual contributions. Since different states play different structural roles in an online state-transition graph built from sampled trajectories, their impacts should be differentiated and converted into task-aware credit at both the step and trajectory levels. We therefore present Graph-Enhanced Policy Optimization (GEPO), a framework for dual-level structural credit assignment in multi-step LLM agent training. Specifically, GEPO derives a state-level Task-Conditioned Criticality score that combines topological betweenness on the state-transition graph with semantic similarity to the task prompt. Based on this score, trajectory-level credit is reshaped through a state-adaptive discount, while step-level credit is scaled by the criticality of its successor state. Experimental results show that GEPO outperforms the strongest baselines by 1.1\% in success rate on ALFWorld, 3.2\% on WebShop, and 3.8\% on average across search-augmented QA tasks at the 7B scale. Compared with flat group-based methods, GEPO reduces across-seed variance and concentrates gradient signals on the most critical steps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_26270 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph-Enhanced Policy Optimization in LLM Agent Training Yuan, Jiazhen Gong, Zhike Hang, Jinquan Bai, Zhengbiao Zhao, Wei Artificial Intelligence Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based reinforcement learning is widely adopted, which reinforces trajectories with higher relative performance within the group. However, in most existing methods, every step within a trajectory and every trajectory with the same terminal reward receive identical credit, regardless of their actual contributions. Since different states play different structural roles in an online state-transition graph built from sampled trajectories, their impacts should be differentiated and converted into task-aware credit at both the step and trajectory levels. We therefore present Graph-Enhanced Policy Optimization (GEPO), a framework for dual-level structural credit assignment in multi-step LLM agent training. Specifically, GEPO derives a state-level Task-Conditioned Criticality score that combines topological betweenness on the state-transition graph with semantic similarity to the task prompt. Based on this score, trajectory-level credit is reshaped through a state-adaptive discount, while step-level credit is scaled by the criticality of its successor state. Experimental results show that GEPO outperforms the strongest baselines by 1.1\% in success rate on ALFWorld, 3.2\% on WebShop, and 3.8\% on average across search-augmented QA tasks at the 7B scale. Compared with flat group-based methods, GEPO reduces across-seed variance and concentrates gradient signals on the most critical steps. |
| title | Graph-Enhanced Policy Optimization in LLM Agent Training |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.26270 |