Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States Paper • 2605.07579 • Published 4 days ago • 12
KL for a KL: On-Policy Distillation with Control Variate Baseline Paper • 2605.07865 • Published 4 days ago • 13
In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents Paper • 2509.01560 • Published Dec 30, 2025 • 4
ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding Paper • 2510.00546 • Published 22 days ago • 14
Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in LLMs Paper • 2509.24319 • Published Sep 29, 2025 • 3