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

arXiv: https://arxiv.org/abs/2608.30397 · HTML: https://mlsanity.com/paper/2608.30397/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment](https://mlsanity.com/paper/2510.07743/) (2025)
- [Training Language Models with Language Feedback at Scale](https://mlsanity.com/paper/2303.16755/) (2023)
- [DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research](https://mlsanity.com/paper/2505.19253/) (2025)
- [Reverse-Engineered Reasoning for Open-Ended Generation](https://mlsanity.com/paper/2509.06160/) (2025)
- [Learning to Refine with Fine-Grained Natural Language Feedback](https://mlsanity.com/paper/2407.02397/) (2024)
- [The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement](https://mlsanity.com/paper/2503.16024/) (2025)
- [Language Models Can Learn from Verbal Feedback Without Scalar Rewards](https://mlsanity.com/paper/2509.22638/) (2025)
- [RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks](https://mlsanity.com/paper/2511.01758/) (2025)
- [Training Language Model to Critique for Better Refinement](https://mlsanity.com/paper/2506.22157/) (2025)
- [Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning](https://mlsanity.com/paper/2510.24320/) (2025)
- [R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning](https://mlsanity.com/paper/2604.03004/) (2026)

## Built on by (most cited first, 1 of 1)

- [Training Advisors for LLM Agents from Task Outcomes](https://mlsanity.com/paper/2610.09858/) (2026)

## Abstract (arXiv)

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 intended weakness. We introduce TAIScore (Targeted Actionable Improvement Score), a reward that evaluates the instruction, initial response, critique, and revision together, assessing whether the critique targets a real weakness, whether the actor follows it, and whether the intended aspect improves. We use this reward to train an actor-tailored critic with GRPO, and use critique-guided refinements to construct DPO preference pairs for the actor, forming a co-evolving critic-actor loop where the critic adapts to the actor's changing capability. Experiments show that an 8B critic trained with TAIScore outperforms both a zero-shot 120B critic and critics trained with outcome-only or critique-only reward signals. Co-evolving the critic and actor further improves performance, suggesting that effective critique supervision should adapt as the actor changes.