Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge
On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
Abstract (arXiv)
Multimodal Large Language Models (MLLMs) have been widely adopted as MLLM-as-a-Judges due to their strong alignment with human judgment across various visual tasks. However, most existing judge models are optimized for single-task scenarios and struggle to generalize to diverse contexts, which is a critical requirement for reliable evaluation. To address this limitation, we propose Multi-Task Reinforcement Learning for MLLM-as-a-Judge (MT-RL-Judge), a framework that jointly optimizes the judge model across multiple tasks, leveraging the generalization capabilities of RL. Experimental results against several strong baselines demonstrate that MT-RL-Judge outperforms strong baselines in both judgment consistency and correlation with human preferences. Furthermore, our approach exhibits robust generalization on out-of-distribution tasks, further validating its effectiveness.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 21 of its 24 references that are in the map. First posted on arXiv 12 Mar 2026.
Builds on
21 of 24 references.
References · 21
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
- 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
- 2024A Survey on LLM-as-a-Judgecited by 1,384
- 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
- 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
- 2023What You See is What You Read? Improving Text-Image Alignment Evaluationcited by 105
- 2024MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMscited by 72
- 2024MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?cited by 64
- 2024UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Imagescited by 52
9 more
- 2025UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learningcited by 41
- 2025Judge Anything: MLLM as a Judge Across Any Modalitycited by 33
- 2024MLLM-as-a-Judge for Image Safety without Human Labelingcited by 23
- 2023Exploring the Naturalness of AI-Generated Imagescited by 22
- 2025MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfacescited by 11
- 2025MR. Judge: Multimodal Reasoner as a Judgecited by 7
- 2025Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluatorscited by 6
- 2025ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judgescited by 1
- 2026Bi-Level Prompt Optimization for Multimodal LLM-as-a-Judgecited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
- 2025Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
- 2025Beyond Monolithic Rewards: A Hybrid and Multi-Aspect Reward Optimization for MLLM Alignment
- 2026Lost in Translation: Do LVLM Judges Generalize Across Languages?
- 2025Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
- 2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
- 2025JudgeLRM: Large Reasoning Models as a Judge
- 2025Improve LLM-as-a-Judge Ability as a General Ability