10 papers
Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember
Zenghuang Fu, Zhaoyang Li, Qiuyuan Ai +6
Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly…
Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
Ante Wang, Jiaqi Fu, Xuanyi Chen +4
Thinking has emerged as a critical capability for Large Language Models (LLMs) tackling complex tasks. However, its reactive nature, where reasoning is passively triggered only upo…
Enhancing LLM Metacognition via Cognitive Pairwise Training
Weitao Li, Hao Zhou, Xuanyu Lei +11
Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when…
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
Zhanyu Liu, Qingguo Hu, Ante Wang +5
Reinforcement Learning with Verifiable Reward (RLVR) has proven effective for training reasoning-oriented large language models, but existing methods largely assume high-resource s…
Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
Jingyi Ren, Ante Wang, Yunghwei Lai +5
Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguis…
Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution
Ante Wang, Weizhi Ma, Yang Liu
Knowing the reliability of a model's response is essential in practical applications. Given the strong generation capabilities of large language models (LLMs), research has focused…