8 papers
LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation
Xingyu Chen, Rui Wang, Zhaopeng Tu +1
Evaluating frontier LLMs is challenging: static benchmarks suffer from contamination and saturation -- leaving users unable to distinguish top models and developers blind to specif…
The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
Xinbei Ma, Ruotian Ma, Xingyu Chen +14
LLM-based multi-agent systems demonstrate great potential for tackling complex problems, but how competition shapes their behavior remains underexplored. This paper investigates th…
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Ziyin Zhang, Jiahao Xu, Zhiwei He +10
Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approache…
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
Zhiwei He, Tian Liang, Jiahao Xu +12
Reinforcement learning (RL) with large language models shows promise in complex reasoning. However, its progress is hindered by the lack of large-scale training data that is suffic…
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Yansi Li, Jiahao Xu, Tian Liang +8
Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Tradi…
RaSA: Rank-Sharing Low-Rank Adaptation
Zhiwei He, Zhaopeng Tu, Xing Wang +7
Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs). However, the limited expressive capacity of LoRA, stem…