activity
20232026
most citedDon't Make Your LLM an Evaluation Benchmark Cheater

18 citations · 25 across the 15 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2026

Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning

Zhipeng Chen, Xiaobo Qin, Wayne Xin Zhao +2

Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the reasoning ability of large language models (LLMs). However, due to the limited amount…

cs.CL2025

From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

Jia Deng, Jie Chen, Zhipeng Chen +7

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditiona…

cs.CL2025

Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning

Jia Deng, Jie Chen, Zhipeng Chen +2

Recently, reinforcement learning with verifiable rewards (RLVR) has been widely used for enhancing the reasoning abilities of large language models (LLMs). A core challenge in RLVR…

cs.CL2025

ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests

Shiyi Xu, Yiwen Hu, Yingqian Min +3

With the significant progress of large reasoning models in complex coding and reasoning tasks, existing benchmarks, like LiveCodeBench and CodeElo, are insufficient to evaluate the…

cs.CL2025

Towards Effective Code-Integrated Reasoning

Fei Bai, Yingqian Min, Beichen Zhang +6

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire thi…

cs.CL20252 cited

R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning

Huatong Song, Jinhao Jiang, Wenqing Tian +7

Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-Augmented Generation (RAG) helps by injecting external information, but cur…