AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning

arXiv:2603.21362v3 Announce Type: replace Abstract: Evaluating LLM agent trajectories is fundamentally task-specific: a code-debugging agent should be judged on Correctness and Error Handling, not on Fluency or Safety. Yet the dominant paradigm -- LLM-as-Judge with a fixed rubric -- applies the...