Agentic Rubrics as Contextual Verifiers for SWE Agents Code

Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction Code

PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach Code

PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning Code Data

Online Rubrics Elicitation from Pairwise Comparisons