ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite with largest gains at the 0.8B scale.
Reinforced mllm: A survey on rl-based reasoning in multimodal large language models
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle diverse modalities such as vision, audio, and video, enabling robust reasoning across multimodal inputs remains challenging. This paper provides a systematic review of recent advances in RL-based reasoning for MLLMs, covering key algorithmic designs, reward mechanism innovations, and practical applications. We highlight two main RL paradigms, value-model-free and value-model-based methods, and analyze how RL enhances reasoning abilities by optimizing reasoning trajectories and aligning multimodal information. Additionally, we provide an extensive overview of benchmark datasets, evaluation protocols, and current limitations, and propose future research directions to address challenges such as sparse rewards, inefficient cross-modal reasoning, and real-world deployment constraints. Our goal is to provide a comprehensive and structured guide to RL-based multimodal reasoning.
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
ThinkDeception introduces MLLMs, a multimodal CoT dataset, and VAC-GRPO progressive RL to convert deception detection into interpretable reasoning and claims new SOTA accuracy plus rationale quality.
AnE combines Truth Anchor Expansion and Scaffold-Stripping to deliver 10.3% gains on eight multimodal reasoning benchmarks for MLLMs.
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
DR-MMSearchAgent derives batch-wide trajectory advantages and uses differentiated Gaussian rewards to prevent premature collapse in multimodal agents, outperforming MMSearch-R1 by 8.4% on FVQA-test.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
A GRPO framework that treats thinking as a tool call and uses dual-level regulation so multimodal models learn when to reason versus answer directly.
OmniJigsaw is a self-supervised proxy task that reconstructs shuffled audio-visual clips via joint integration, sample-level selection, and clip-level masking strategies, yielding gains on 15 video, audio, and reasoning benchmarks.
OneThinker unifies image and video reasoning in one model across 10 tasks via a 600k corpus, CoT-annotated SFT, and EMA-GRPO reinforcement learning, reporting strong results on 31 benchmarks plus some cross-task transfer.
The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.
citing papers explorer
-
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite with largest gains at the 0.8B scale.
-
CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.
-
ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection
ThinkDeception introduces MLLMs, a multimodal CoT dataset, and VAC-GRPO progressive RL to convert deception detection into interpretable reasoning and claims new SOTA accuracy plus rationale quality.
-
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
AnE combines Truth Anchor Expansion and Scaffold-Stripping to deliver 10.3% gains on eight multimodal reasoning benchmarks for MLLMs.
-
From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding
A group-revision paradigm for GRPO-based RL fine-tuning of VLMs converts failure responses into improvement signals that refine rewards and advantages, yielding gains on referring segmentation, REC, and counting benchmarks.
-
Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
Introduces VURB benchmark and VUP-35K dataset to train discriminative and generative video reward models that achieve SOTA performance on VURB and VideoRewardBench.
-
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
DR-MMSearchAgent derives batch-wide trajectory advantages and uses differentiated Gaussian rewards to prevent premature collapse in multimodal agents, outperforming MMSearch-R1 by 8.4% on FVQA-test.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
-
Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning
A GRPO framework that treats thinking as a tool call and uses dual-level regulation so multimodal models learn when to reason versus answer directly.
-
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
OmniJigsaw is a self-supervised proxy task that reconstructs shuffled audio-visual clips via joint integration, sample-level selection, and clip-level masking strategies, yielding gains on 15 video, audio, and reasoning benchmarks.
-
OneThinker: All-in-one Reasoning Model for Image and Video
OneThinker unifies image and video reasoning in one model across 10 tasks via a 600k corpus, CoT-annotated SFT, and EMA-GRPO reinforcement learning, reporting strong results on 31 benchmarks plus some cross-task transfer.
-
Rethinking Agentic Reinforcement Learning In Large Language Models
The paper reviews conceptual foundations, methodological innovations, effective designs, critical challenges, and future directions for LLM-based Agentic Reinforcement Learning.