collaborators

6 papers

cs.LG2026

RL: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification

Weijie Shi, Yanxi Chen, Zexi Li +5

Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers…

cs.LG2026

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Wenhao Zhang, Yuexiang Xie, Yuchang Sun +5

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Mod…

cs.LG2026

Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends

Chaorui Yao, Yanxi Chen, Yuchang Sun +5

Off-policy reinforcement learning (RL) for large language models (LLMs) is attracting growing interest, driven by practical constraints in real-world applications, the complexity o…

cs.LG2026

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models

Shumin Wang, Yuexiang Xie, Wenhao Zhang +4

Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models (LLMs), providing valuable insights into their exploration capabilitie…

cs.LG2025

Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models

Xuchen Pan, Yanxi Chen, Yushuo Chen +11

Trinity-RFT is a general-purpose, unified and easy-to-use framework designed for reinforcement fine-tuning (RFT) of large language models. It is built with a modular and decoupled…

cs.LG2025

Enhancing Latent Computation in Transformers with Latent Tokens

Yuchang Sun, Yanxi Chen, Yaliang Li +1

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method t…