SEAR: Self-Judging Agentic Reward Models
Abstract
AbstractAgentic reward models enhance large language model (LLM) evaluation by incorporating external tool-use capabilities. However, their training is heavily constrained by coarse-grained outcome supervision and the high cost of process-level annotations. To address these challenges, we propose SEAR (Self-judging agentic reward models), a novel training framework that enables agentic reward models to self-judge their own judging processes. SEAR introduces a dual-role adversarial co-evolution framework, where the model alternates between a judger and a self-judger within a single generation process: the judger is optimized to produce more rigorous reasoning trajectories that maximize self-judgment scores, while the self-judger learns to provide critical and discriminative evaluations. Moreover, SEAR further enables agentic RMs to self-evolve without relying on external human annotations. Extensive experiments demonstrate that SEAR consistently improves the reliability of agentic reward models across diverse benchmarks.