5 papers
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
Yongcan Yu, Lingxiao He, Jian Liang +5
Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through…
The Trinity of Consistency as a Defining Principle for General World Models
Jingxuan Wei, Siyuan Li, Yuhang Xu +21
The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial Gene…
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Yuanda Xu, Hejian Sang, Zhengze Zhou +2
Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suf…
AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards
Zihan Lin, Xiaohan Wang, Hexiong Yang +5
While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential…
ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
Zihan Lin, Xiaohan Wang, Jie Cao +4
Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for…