Paper Detail
Haixin Wang, Hejie Cui, Chenwei Zhang, Xin Liu, Shuowei Jin, Shijie Geng, Xinyang Zhang, Nasser Zalmout, Zhenyu Shi, Yizhou Sun
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{wang2026t,
title = {T\textasciicircum{}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},
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 uncertai},
url = {https://huggingface.co/papers/2605.02178},
keywords = {multi-turn reinforcement learning, policy optimization, uncertainty awareness, fine-grained exploration, trajectory filtering, credit assignment, training stability, reinforcement learning, code available, huggingface daily},
eprint = {2605.02178},
archiveprefix = {arXiv},
}
{}