1 citations · 2 across the 21 of their papers we have counts for
19 papers
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Jing Liang, Hongyao Tang, Yi Ma +9
Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. O…
Complementary RL: Towards Efficient Experience-Driven Agent Learning
Dilxat Muhtar, Jiashun Liu, Wei Gao +8
Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome fe…
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria
Xinyu Hu, Yancheng He, Weixun Wang +6
Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, th…
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…
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Weixun Wang, XiaoXiao Xu, Wanhe An +86
Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its impo…
RollArt: Disaggregated Multi-Task Agentic RL Training at Scale
Wei Gao, Yuheng Zhao, Tianyuan Wu +15
Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU…
Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
Jiashun Liu, Johan Obando-Ceron, Han Lu +7
Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely pragmatic: conventional value functions are…
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…
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…
MeSH: Memory-as-State-Highways for Recursive Transformers
Chengting Yu, Xiaobo Shu, Yadao Wang +8
Recursive transformers reuse parameters and iterate over hidden states multiple times, decoupling compute depth from parameter depth. However, under matched compute, recursive mode…
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
Zihe Liu, Jiashun Liu, Yancheng He +13
Reinforcement learning for LLM reasoning has rapidly emerged as a prominent research area, marked by a significant surge in related studies on both algorithmic innovations and prac…
Think-J: Learning to Think for Generative LLM-as-a-Judge
Hui Huang, Yancheng He, Hongli Zhou +5
LLM-as-a-Judge refers to the automatic modeling of preferences for responses generated by Large Language Models (LLMs), which is of significant importance for both LLM evaluation a…
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
Yancheng He, Shilong Li, Jiaheng Liu +8
Recently, o1-like models have drawn significant attention, where these models produce the long Chain-of-Thought (CoT) reasoning steps to improve the reasoning abilities of existing…
Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation
Yijia Luo, Yulin Song, Xingyao Zhang +5
Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning. The R1 distillation scheme ha…
AIR: Complex Instruction Generation via Automatic Iterative Refinement
Wei Liu, Yancheng He, Hui Huang +5
With the development of large language models, their ability to follow simple instructions has significantly improved. However, adhering to complex instructions remains a major cha…
ProgCo: Program Helps Self-Correction of Large Language Models
Xiaoshuai Song, Yanan Wu, Weixun Wang +3
Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine their initial responses without external feedback. However, LLMs often fail to effectivel…
WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis
Chengwei Hu, Jianhui Zheng, Yancheng He +7
Recent advancements in autonomous multi-agent systems (MAS) based on large language models (LLMs) have enhanced the application scenarios and improved the capability of LLMs to han…
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
Yancheng He, Shilong Li, Jiaheng Liu +15
New LLM evaluation benchmarks are important to align with the rapid development of Large Language Models (LLMs). In this work, we present Chinese SimpleQA, the first comprehensive…
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision
Shilong Li, Yancheng He, Hui Huang +7
Recent advancements in Direct Preference Optimization (DPO) have significantly enhanced the alignment of Large Language Models (LLMs) with human preferences, owing to its simplicit…