Author

Xintong Li

h-index 13 View on Semantic Scholar

We have 2 of 55 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts

Across verifiable reasoning, open-ended generation, and post-SFT settings, RRPO remains competitive with verifier-based optimization, improves over weakly supervised baselines, and provides additional gains after supervised fine-tuning.

Yuxin Xiong, Xun-Yi Jiang, Rohan Surana et al. · arXiv.org · 0 citations

Jul 2026

Process Reward Informed Tree Rollout for Effective Multi-Turn RL

This work proposes Process-Scorer Guided Adaptive Tree Rollout (PATR), a quality-aware rollout framework for multi-turn agent RL that uses task-appropriate process feedback to score partial trajectories, selectively branches from promising states, reuses shared prefixes, and conservatively stops degenerate paths to red...

Xintong Li, Sha Li, Yuwei Zhang et al. · arXiv.org · 0 citations