SOURCE-LINKED INTELLIGENCE

Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Natural-language critiques provide supervision beyond scalar rewards for non-verifiable generation, which lacks deterministic verifiers. In critique-guided refinement, a critic gives feedback on an initial response and an actor revises it. However, final revision quality does not reveal whether the critique was actually useful: a capable actor may improve without following the feedback, while valid feedback may fail if the actor cannot execute it. We frame critique as actor-conditioned revision guidance, where usefulness depends on whether the feedback helps the target actor address the intend

Read original source ↗ Open in workspace

recordType

paper

region

Global