# LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

arXiv: https://arxiv.org/abs/2509.00676 · HTML: https://mlsanity.com/paper/2509.00676/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 57 of its 63 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 57)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset](https://mlsanity.com/paper/2402.14804/) (2024)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning](https://mlsanity.com/paper/2504.08837/) (2025)
- [MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning](https://mlsanity.com/paper/2503.07365/) (2025)

## Built on by (most cited first, 30 of 35)

- [Scaling Agent Learning via Experience Synthesis](https://mlsanity.com/paper/2511.03773/) (2025)
- [Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning](https://mlsanity.com/paper/2511.19900/) (2025)
- [Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch](https://mlsanity.com/paper/2512.02395/) (2025)
- [Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image](https://mlsanity.com/paper/2512.16899/) (2025)
- [Generative Universal Verifier as Multimodal Meta-Reasoner](https://mlsanity.com/paper/2510.13804/) (2025)
- [Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following](https://mlsanity.com/paper/2511.21662/) (2025)
- [Unified Personalized Reward Model for Vision Generation](https://mlsanity.com/paper/2602.02380/) (2026)
- [PhyCritic: Multimodal Critic Models for Physical AI](https://mlsanity.com/paper/2602.11124/) (2026)
- [Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy](https://mlsanity.com/paper/2601.06801/) (2026)
- [When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning](https://mlsanity.com/paper/2603.21289/) (2026)
- [Watch Before You Answer: Learning from Visually Grounded Post-Training](https://mlsanity.com/paper/2604.05117/) (2026)
- [PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs](https://mlsanity.com/paper/2512.14944/) (2025)
- [Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization](https://mlsanity.com/paper/2602.21743/) (2026)
- [Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model](https://mlsanity.com/paper/2601.04033/) (2026)
- [Agentic Critical Training](https://mlsanity.com/paper/2603.08706/) (2026)
- [Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving](https://mlsanity.com/paper/2604.27366/) (2026)
- [SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models](https://mlsanity.com/paper/2604.20705/) (2026)
- [Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation](https://mlsanity.com/paper/2608.24138/) (2026)
- [VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment](https://mlsanity.com/paper/2511.17962/) (2025)
- [High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models](https://mlsanity.com/paper/2512.21815/) (2025)
- [Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate](https://mlsanity.com/paper/2601.22297/) (2026)
- [Towards Better RL Training Data Utilization via Second-Order Rollout](https://mlsanity.com/paper/2602.22765/) (2026)
- [Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models](https://mlsanity.com/paper/2605.07872/) (2026)
- [Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation](https://mlsanity.com/paper/2605.19639/) (2026)
- [AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution](https://mlsanity.com/paper/2605.25571/) (2026)
- [Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling](https://mlsanity.com/paper/2604.05445/) (2026)
- [DT2IT-MRM: Debiased Preference Construction and Iterative Training for Multimodal Reward Modeling](https://mlsanity.com/paper/2604.19544/) (2026)
- [Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety](https://mlsanity.com/paper/2606.25034/) (2026)
- [SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning](https://mlsanity.com/paper/2607.13931/) (2026)
- [Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift](https://mlsanity.com/paper/2607.17524/) (2026)

## Abstract (arXiv)

In vision-language modeling, critic models are typically trained to evaluate outputs -- assigning scalar scores or pairwise preferences -- rather than to generate responses. This separation from policy models, which produce the responses, is so entrenched that critics are rarely considered for direct policy use. In this work, we challenge this convention. We propose to reorganize preference-labeled critic datasets into verifiable training signals and perform reinforcement learning directly on a base generative model, producing LLaVA-Critic-R1, a multimodal critic trained to optimize preference judgments while retaining full generation ability. Surprisingly, LLaVA-Critic-R1 emerges not only as a top-performing critic but also as a competitive policy model -- matching or surpassing specialized reasoning VLMs trained with in-domain data across 26 visual reasoning and understanding benchmarks, with an average gain of +5.7% over its base model (Qwen-2.5-VL-7B). Extending this approach to existing strong reasoning VLMs yields LLaVA-Critic-R1+, which further advances policy performance without sacrificing critic quality, achieving a SoTA performance of 71.9 on MMMU at the 7B scale. Finally, we show that the enhanced critic ability benefits inference: applying self-critique at test time yields an average +13.8% improvement on five representative reasoning tasks without additional training. Our results reveal that RL training on critic data can produce a unified model excelling at both evaluation and generation, offering a simple path toward scalable, self-improving multimodal systems.