| title | T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning |
|---|---|
| authors | Haixin Wang, Hejie Cui, Chenwei Zhang, Xin Liu, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun |
| date | 2026-05-04 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.02178 |
| upvotes | 9 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse. We argue that this instability stems from inefficient exploration in multi-turn settings, where policies continue to generate low-information actions that neither reduce uncertainty nor advance task progress. To address this issue, we propose Token- and Turn-level Policy Optimization (T^2PO), an uncertainty-aware framework that explicitly controls exploration at fine-grained levels. At the token level, T^2PO monitors uncertainty dynamics and triggers a thinking intervention once the marginal uncertainty change falls below a threshold. At the turn level, T^2PO identifies interactions with negligible exploration progress and dynamically resamples such turns to avoid wasted rollouts. We evaluate T^2PO in diverse environments, including WebShop, ALFWorld, and Search QA, demonstrating substantial gains in training stability and performance improvements with better exploration efficiency. Code is available at: https://github.com/WillDreamer/T2PO. |
cite
@misc{wang2026t,
title={T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning},
author={Haixin Wang and Hejie Cui and Chenwei Zhang and Xin Liu and Shuowei Jin and Shijie Geng and Xinyang Zhang and Nasser Zalmout and Zhenyu Shi and Yizhou Sun},
year={2026},
eprint={2605.02178},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.02178}
}