collaborators

9 papers

cs.LG2026

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

Zhichen Dong, Yang Li, Yuhan Sun +9

Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing t…

cs.CL2026

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

Yang Li, Zhichen Dong, Yuhan Sun +9

The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the dis…

cs.LG2026

One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning

Yiyuan Li, Zhen Huang, Yanan Wu +6

The reasoning ability of large language models (LLMs) can be unleashed with reinforcement learning (RL) (OpenAI, 2024; DeepSeek-AI et al., 2025a; Zeng et al., 2025). The success of…

cs.CL2026

DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning

Weize Liu, Yongchi Zhao, Yijia Luo +8

Large language models (LLMs) perform strongly on many language tasks but still struggle with complex multi-step reasoning across disciplines. Existing reasoning datasets often lack…

cs.AI2026

Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement

Mingyu Xu, Cheng Fang, Keyue Jiang +16

We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest…

cs.LG2025

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony

Han Lu, Zichen Liu, Shaopan Xiong +19

Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems desi…