6 papers
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
Haoxiang Sun, Yingqian Min, Zhipeng Chen +2
The rapid advancement of large reasoning models has saturated existing math benchmarks, underscoring the urgent need for more challenging evaluation frameworks. To address this, we…
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…
Virgo: A Preliminary Exploration on Reproducing o1-like MLLM
Yifan Du, Zikang Liu, Yifan Li +7
Recently, slow-thinking reasoning systems, built upon large language models (LLMs), have garnered widespread attention by scaling the thinking time during inference. There is also…
Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao +1
Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue. Typical text generation approaches adopt an auto-regressive generation wi…
Enhancing LLM Reasoning with Reward-guided Tree Search
Jinhao Jiang, Zhipeng Chen, Yingqian Min +12
Recently, test-time scaling has garnered significant attention from the research community, largely due to the substantial advancements of the o1 model released by OpenAI. By alloc…
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
Yingqian Min, Zhipeng Chen, Jinhao Jiang +11
Recently, slow-thinking reasoning systems, such as o1, have demonstrated remarkable capabilities in solving complex reasoning tasks. These systems typically engage in an extended t…