Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation Paper • 2601.14691 • Published Jan 21 • 1
ThinkPRM Collection Process Reward Models that Think -- https://arxiv.org/abs/2504.16828 • 8 items • Updated Jul 29, 2025 • 6
ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists Paper • 2506.01241 • Published Jun 2, 2025 • 9
ThinkPRM Collection Process Reward Models that Think -- https://arxiv.org/abs/2504.16828 • 8 items • Updated Jul 29, 2025 • 6