RL for VLMs

RL: Reinforcement Learning · VLM: Vision-Language Model

Ask about this topic

Overview

This field studies how reinforcement learning can improve models that interpret images or video alongside language, and sometimes take actions in visual environments. Common approaches include group-relative policy optimization, PPO, and reinforcement learning from verifiable rewards, with feedback based on answer correctness, visual evidence, intermediate reasoning, preferences, or tool use. Applications range from image and video question answering, spatial reasoning, and medical analysis to navigation and robotic manipulation. A central challenge is ensuring that better scores reflect genuine use of visual evidence rather than language shortcuts, while designing reliable rewards and efficient training that generalize beyond the training setting.

Latest papers

CardsList

476 papers68 papers in the last four weeks, up 94% on the four weeks before. 0.4% of all new papers.

Apr 9, 2026

Fundus-R1: Training a Fundus-Reading MLLM on Public Data

Fundus imaging such as CFP, OCT and UWF is crucial for the early detection of retinal anomalies and diseases. Fundus image understanding, due to its knowledge-intensive nature, poses a challenging vision-language task. An emerging approach to addressing the task is to post-train a generic multimodal large language model (MLLM), either by supervised finetuning (SFT) or by reinforcement learning with verifiable rewards (RLVR), on a considerable amount of in-house samples paired with high-quality clinical reports. However, these valuable samples are not publicly accessible, which not only hinders reproducibility but also practically limits research to few players. To overcome the barrier, we make a novel attempt to train a reasoning-enhanced fundus-reading MLLM, which we term Fundus-R1, using exclusively public datasets, wherein over 94% of the data are annotated with only image-level labels. Our technical contributions are two-fold. First, we propose a RAG-based method for composing image-specific, knowledge-aware reasoning traces. Such auto-generated traces link visual findings identified by a generic MLLM to the image labels in terms of ophthalmic knowledge. Second, we enhance RLVR with a process reward that encourages self-consistency of the generated reasoning trace in each rollout. Extensive experiments on three fundus-reading benchmarks, i.e., FunBench, Omni-Fundus and GMAI-Fundus, show that Fundus-R1 clearly outperforms multiple baselines, including its generic counterpart (Qwen2.5-VL) and a stronger edition post-trained without using the generated traces. This work paves the way for training powerful fundus-reading MLLMs with publicly available data.

Yuchuan Deng, Qijie Wei, Kaiheng Qian +6

Renmin University of China, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China · Zhejiang Gongshang University, China

Medical VLMsMedical ImagingFundus ImagingRL for VLMsProcess Reward Models
AskPDF
Apr 9, 2026

MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning

Medical Vision-Language Models (VLMs) hold immense promise for complex clinical tasks, but their reasoning capabilities are often constrained by text-only paradigms that fail to ground inferences in visual evidence. This limitation not only curtails performance on tasks requiring fine-grained visual analysis but also introduces risks of visual hallucination in safety-critical applications. Thus, we introduce MedVR, a novel reinforcement learning framework that enables annotation-free visual reasoning for medical VLMs. Its core innovation lies in two synergistic mechanisms: Entropy-guided Visual Regrounding (EVR) uses model uncertainty to direct exploration, while Consensus-based Credit Assignment (CCA) distills pseudo-supervision from rollout agreement. Without any human annotations for intermediate steps, MedVR achieves state-of-the-art performance on diverse public medical VQA benchmarks, significantly outperforming existing models. By learning to reason directly with visual evidence, MedVR promotes the robustness and transparency essential for accelerating the clinical deployment of medical AI.

Zheng Jiang, Heng Guo, Chengyu Fang +4

Tsinghua University · DAMO Academy, Alibaba Group · Hupan Lab, 310023, Hangzhou, China +2

VLM ReasoningVisual ReasoningMedical VLMsRL for VLMsMedical VQA
AskPDF
Apr 8, 2026

Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs

Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to extract semantics in multi-step reasoning. We propose "Decompose, Look, and Reason" (DLR), a reinforced latent reasoning framework that dynamically decomposes queries into textual premises, extracts premise-conditioned continuous visual latents, and deduces answers through grounded rationales. We introduce a three-stage training pipeline and propose a novel Spherical Gaussian Latent Policy, to enable effective exploration in the latent space. Extensive experiments on vision-centric benchmarks show that DLR consistently outperforms strong baselines, including text-only, interleaved multimodal CoT, and latent reasoning methods, while providing superior stepwise interpretability.

Mengdan Zhu, Senhao Cheng, Liang Zhao

Emory University · University of Michigan, Ann Arbor

Vision-Language GroundingVLM InterpretabilityLatent Visual ReasoningRL for VLMsVLM ReasoningVisually Grounded Reasoning+1
AskPDF
Apr 7, 2026

Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank

Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vision-language models (VLMs) to assess perceptual quality. However, existing approaches operate at a single granularity, predicting only an overall quality score, while overlooking the multi-dimensional nature of human quality perception, which encompasses attributes such as sharpness, color fidelity, noise level, and compositional aesthetics. In this paper, we propose MG-IQA (Multi-Granularity IQA), a multi-granularity reasoning framework that extends RL2R to jointly assess overall image quality and fine-grained quality attributes within a single inference pass. Our approach introduces three key innovations: (1) an attribute-aware prompting strategy that elicits structured multi-attribute reasoning from VLMs; (2) a multi-dimensional Thurstone reward model that computes attribute-specific fidelity rewards for group relative policy optimization; and (3) a cross-domain alignment mechanism that enables stable joint training across synthetic distortion, authentic distortion, and AI-generated image datasets without perceptual scale re-alignment. Extensive experiments on eight IQA benchmarks demonstrate that MG-IQA consistently outperforms state-of-the-art methods in both overall quality prediction (average SRCC improvement of 2.1%) and attribute-level assessment, while generating interpretable, human-aligned quality descriptions.

Xiangyong Chen, Xiaochuan Lin, Haoran Liu +3

Henan Polytechnic University

Image Quality AssessmentVLM ReasoningRL for VLMs
AskPDF
Apr 6, 2026

Vero: An Open RL Recipe for General Visual Reasoning

What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language models (VLMs) suggest that broad visual reasoning is within reach, yet their closed data and reinforcement learning (RL) pipelines make their gains difficult to study, reproduce, or extend. We introduce Vero, a family of fully open VLMs that match or exceed existing open-weight models across diverse visual reasoning tasks. We scale RL data and rewards across six broad task categories, constructing Vero-600K, a 600K-sample dataset from 59 datasets, and designing task-routed rewards that handle heterogeneous answers. Across VeroEval, our 30-benchmark suite, Vero-600K outperforms existing RL datasets under controlled comparisons. Applied to five starting models, Vero variants gain 2.9-5.4 points on average over their initial models. Notably, Vero-Qwen3I-8B, trained on the Instruct model, surpasses Qwen3-VL-8B-Thinking by 3.8 points on average without additional distillation. Systematic ablations reveal that different task categories elicit distinct reasoning patterns and that broad gains depend on learning them jointly rather than in isolation. All data, code, and models are publicly available.

Gabriel Sarch, Linrong Cai, Qunzhong Wang +3

Princeton University

Reasoning for VLMsVisual ReasoningLarge Vision-Language ModelsVLM ReasoningRL for VLMs
AskPDF
Apr 6, 2026

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward

Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lean more on textual cues than visual evidence and the risk of producing ungrounded or fabricated responses. To address these issues, we propose Saliency-R1, a framework for improving the interpretability and faithfulness of VLMs reasoning. Specifically, we introduce a novel saliency map technique that efficiently highlights critical image regions contributing to generated tokens without additional computational overhead. This can further be extended to trace how visual information flows through the reasoning process to the final answers, revealing the alignment between the thinking process and the visual context. We use the overlap between the saliency maps and human-annotated bounding boxes as the reward function, and apply Group Relative Policy Optimization (GRPO) to align the salient parts and critical regions, encouraging models to focus on relevant areas when conduct reasoning. Experiments show Saliency-R1 improves reasoning faithfulness, interpretability, and overall task performance.

Shizhan Gong, Minda Hu, Qiyuan Zhang +2

The Chinese University of Hong Kong, Hong Kong, China · City University of Hong Kong, Hong Kong, China

VLM ReasoningFaithfulness in VLMsVLM InterpretabilityVision-Language GroundingRL for VLMs
AskPDF
Apr 6, 2026

Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning

Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evidence-aligned. We introduce Reinforce to Learn, Elect to Reason (RLER), a dual paradigm that decouples learning to produce evidence from obtaining a reliable answer. In RLER-Training, we optimize the policy with group-relative reinforcement learning (RL) and 3 novel task-driven rewards: Frame-sensitive reward grounds reasoning on explicit key frames, Think-transparency reward shapes readable and parsable reasoning traces, and Anti-repetition reward boosts information density. These signals teach the model to emit structured, machine-checkable evidence and potentiate reasoning capabilities. In RLER-Inference, we apply a train-free orchestrator that generates a small set of diverse candidates, parses their answers and cited frames, scores them by evidence consistency, confidence, transparency, and non-redundancy, and then performs a robust evidence-weighted election. This closes the loop between producing and using evidence, improving reliability and interpretability without enlarging the model. We comprehensively evaluate RLER against various open-source and RL-based LMMs on 8 representative benchmarks. RLER achieves state of the art across all benchmarks and delivers an average improvement of 6.3% over base models, while using on average 3.1 candidates per question, indicating a favorable balance between compute and quality. The results support a simple thesis: making evidence explicit during learning and electing by evidence during inference is a robust path to trustworthy video reasoning.

Songyuan Yang, Weijiang Yu, Jilin Ma +5

National University of Defense Technology · Sun Yat-sen University

Video ReasoningVLM InferenceRL for Video ReasoningRL for VLMs
AskPDF
Apr 3, 2026

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large Language Models (MLLMs) to enhance their visual reasoning capabilities. Although many studies have reported improved performance, it remains unclear whether RL training truly enables models to learn from visual information. In this work, we propose the Hallucination-as-Cue Framework, an analytical framework designed to investigate the effects of RL-based post-training on multimodal reasoning models from the perspective of model hallucination. Specifically, we introduce hallucination-inductive, modality-specific corruptions that remove or replace essential information required to derive correct answers, thereby forcing the model to reason by hallucination. By applying these corruptions during both training and evaluation, our framework provides a unique perspective for diagnosing RL training dynamics and understanding the intrinsic properties of datasets. Through extensive experiments and analyses across multiple multimodal reasoning benchmarks, we reveal that the role of model hallucination for RL-training is more significant than previously recognized. For instance, we find that RL post-training under purely hallucination-inductive settings can still significantly improve models' reasoning performance, and in some cases even outperform standard training. These findings challenge prevailing assumptions about MLLM reasoning training and motivate the development of more modality-aware RL-based training designs.

Gengwei Zhang, Jie Peng, Zhen Tan +6

University of North Carolina at Chapel Hill · University of Science and Technology of China · Arizona State University +1

RL for VLMsMultimodal ReasoningVLM HallucinationMultimodal Model Evaluation
AskPDF
Apr 3, 2026

Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models

The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Beyond pattern recognition, linguistic reasoning must integrate with visual comprehension, particularly for Chart Question Answering (CQA) tasks involving complex data visualizations. Current VLMs face significant limitations in CQA, including imprecise numerical extraction, difficulty interpreting implicit visual relationships, and inadequate attention mechanisms for capturing spatial relationships in charts. In this work, we address these challenges by presenting Chart-RL, a novel reinforcement learning framework that enhances VLMs chart understanding through feedback-driven policy optimization of visual perception and logical inference. Our key innovation includes a comprehensive framework integrating Reinforcement Learning (RL) from Policy Optimization techniques along with adaptive reward functions, that demonstrates superior performance compared to baseline foundation models and competitive results against larger state-of-the-art architectures. We also integrated Parameter-Efficient Fine-Tuning through Low-Rank Adaptation (LoRA) in the RL framework that only requires single GPU configurations while preserving performance integrity. We conducted extensive benchmarking across open-source, proprietary, and state-of-the-art closed-source models utilizing the ChartQAPro dataset. The RL fine-tuned Qwen3-VL-4B-Instruct model achieved an answer accuracy of 0.634, surpassing the 0.580 accuracy of the Qwen3-VL-8B-Instruct foundation model despite utilizing half the parameter count, while simultaneously reducing inference latency from 31 seconds to 9 seconds.

Yunfei Bai, Amit Dhanda, Shekhar Jain

Amazon

Chart QAVLM ReasoningRL for VLMs
AskPDF
Apr 2, 2026

Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models

While Reinforcement Learning from Verifiable Rewards (RLVR) has advanced reasoning in Large Vision-Language Models (LVLMs), prevailing frameworks suffer from a foundational methodological flaw: by distributing identical advantages across all generated tokens, these methods inherently dilute the learning signals essential for optimizing the critical, visually-grounded steps of multimodal reasoning. To bridge this gap, we formulate Token Visual Dependency, quantifying the causal information gain of visual inputs via the Kullback-Leibler (KL) divergence between visual-conditioned and text-only predictive distributions. Revealing that this dependency is highly sparse and semantically pivotal, we introduce Perception-Grounded Policy Optimization (PGPO), which is a novel fine-grained credit assignment framework that dynamically reshapes advantages at the token level. Through a threshold-gated, mass-conserving mechanism, PGPO actively amplifies learning signals for visually-dependent tokens while suppressing gradient noise from linguistic priors. Extensive experiments based on the Qwen2.5-VL series across seven challenging multimodal reasoning benchmarks demonstrate that PGPO boosts models by 18.7% on average. Both theoretical and empirical analyses confirm that PGPO effectively reduces gradient variance, prevents training collapse, and acts as a potent regularizer for robust, perception-grounded multimodal reasoning. Code will be released on https://github.com/Yzk1114/PGPO.

Zekai Ye, Qiming Li, Xiaocheng Feng +6

Harbin Institute of Technology · Peng Cheng Laboratory · Huawei Technologies Co., Ltd

RL for VLMsLarge Vision-Language ModelsVLM ReasoningToken-Level Credit Assignment
AskPDF
Apr 2, 2026

STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering

We introduce STRIVE (SpatioTemporal Reinforcement with Importance-aware Variant Exploration), a structured reinforcement learning framework for video question answering. While group-based policy optimization methods have shown promise in large multimodal models, they often suffer from low reward variance when responses exhibit similar correctness, leading to weak or unstable advantage estimates. STRIVE addresses this limitation by constructing multiple spatiotemporal variants of each input video and performing joint normalization across both textual generations and visual variants. By expanding group comparisons beyond linguistic diversity to structured visual perturbations, STRIVE enriches reward signals and promotes more stable and informative policy updates. To ensure exploration remains semantically grounded, we introduce an importance-aware sampling mechanism that prioritizes frames most relevant to the input question while preserving temporal coverage. This design encourages robust reasoning across complementary visual perspectives rather than overfitting to a single spatiotemporal configuration. Experiments on six challenging video reasoning benchmarks including VideoMME, TempCompass, VideoMMMU, MMVU, VSI-Bench, and PerceptionTest demonstrate consistent improvements over strong reinforcement learning baselines across multiple large multimodal models. Our results highlight the role of structured spatiotemporal exploration as a principled mechanism for stabilizing multimodal reinforcement learning and improving video reasoning performance.

Emad Bahrami, Olga Zatsarynna, Parth Pathak +3

University of Bonn · Lamarr Institute for Machine Learning and Artificial Intelligence · Meta +1

Video QARL for Video ReasoningRL for VLMsVideo Reasoning
AskPDF
Apr 1, 2026

Reinforcing Consistency in Video MLLMs with Structured Rewards

Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer from poor visual and temporal grounding: a model may fabricate object existence, assign incorrect attributes, or collapse repeated events while still producing a globally reasonable caption or answer. We study this failure mode through a compositional consistency audit that decomposes a caption into supporting factual and temporal claims, investigating whether a correct high-level prediction is actually backed by valid lower-level evidence. Our top-down audit reveals that even correct root relational claims often lack reliable attribute and existence support. This indicates that standard sentence-level supervision is a weak proxy for faithful video understanding. Furthermore, when turning to reinforcement learning (RL) for better alignment, standard sentence-level rewards often prove too coarse to accurately localize specific grounding failures. To address this, we replace generic sentence-level rewards with a structured reward built from factual and temporal units. Our training objective integrates three complementary components: (1) an instance-aware scene-graph reward for factual objects, attributes, and relations; (2) a temporal reward for event ordering and repetition; and (3) a video-grounded VQA reward for hierarchical self-verification. Across temporal, general video understanding, and hallucination-oriented benchmarks, this objective yields consistent gains on open-source backbones. These results suggest that structured reward shaping is a practical route to more faithful video understanding.

Yihao Quan, Zeru Shi, Jinman Zhao +1

Rutgers University · University of Toronto

Video-Language ModelsObject Hallucination in VLMsRL for VLMsTemporal Video UnderstandingMultimodal Reward Modeling
AskPDF
Apr 1, 2026

All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models

Recent studies have demonstrated that Reinforcement Learning (RL), notably Group Relative Policy Optimization (GRPO), can intrinsically elicit and enhance the reasoning capabilities of Vision-Language Models (VLMs). However, despite the promise, the underlying mechanisms that drive the effectiveness of RL models as well as their limitations remain underexplored. In this paper, we highlight a fundamental behavioral distinction between RL and base models, where the former engages in deeper yet narrow reasoning, while base models, despite less refined along individual path, exhibit broader and more diverse thinking patterns. Through further analysis of training dynamics, we show that GRPO is prone to diversity collapse, causing models to prematurely converge to a limited subset of reasoning strategies while discarding the majority of potential alternatives, leading to local optima and poor scalability. To address this, we propose Multi-Group Policy Optimization (MUPO), a simple yet effective approach designed to incentivize divergent thinking across multiple solutions, and demonstrate its effectiveness on established benchmarks. Project page: https://xytian1008.github.io/MUPO/

Xinyu Tian, Shu Zou, Zhaoyuan Yang +3

Australian National University · Shanghai AI Lab · GE Research

RL for VLMsVLM Reasoning
AskPDF
Mar 30, 2026

Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning

Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that updates both perception and reasoning using a shared reward based solely on the final answer. This shared reward blurs credit assignment, frequently improving reasoning patterns while failing to reliably enhance the accuracy of upstream visual evidence extraction. To address this perception bottleneck, we introduce PRCO (Perception-Reasoning Coevolution), a dual-role RLVR framework with a shared policy. PRCO consists of two cooperative roles: an Observer that generates an evidence caption tailored to the question and a Solver that predicts the final answer based on this caption. Crucially, PRCO employs role-specific reward signals: the Solver is optimized using verifiable outcome rewards on the final answer, while the Observer receives a utility reward derived from the Solver's downstream success. Extensive experiments across eight challenging multimodal reasoning benchmarks demonstrate that PRCO yields consistent improvements across model scales by over 7 points on average accuracy compared to the base model, outperforming prior open-source RL-tuned baselines.

Ziqi Miao, Haonan Jia, Lijun Li +4

Multimodal ReasoningMultimodal Large Language ModelsRL for VLMsReinforcement Learning with Verifiable Rewards
AskPDF
Mar 30, 2026

AutoDrive-P3AutoDrive\text{-}P^3: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning

Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However, current VLM-based approaches suffer from two major limitations: 1) Some VLMs directly output planning results without chain-of-thought (CoT) reasoning, bypassing crucial perception and prediction stages which creates a significant domain gap and compromises decision-making capability; 2) Other VLMs can generate outputs for perception, prediction, and planning tasks but employ a fragmented decision-making approach where these modules operate separately, leading to a significant lack of synergy that undermines true planning performance. To address these limitations, we propose AutoDrive-P3{AutoDrive\text{-}P^3}, a novel framework that seamlessly integrates P\textbf{P}erception, P\textbf{P}rediction, and P\textbf{P}lanning through structured reasoning. We introduce the P3-CoT{P^3\text{-}CoT} dataset to facilitate coherent reasoning and propose P3-GRPO{P^3\text{-}GRPO}, a hierarchical reinforcement learning algorithm that provides progressive supervision across all three tasks. Specifically, AutoDrive-P3{AutoDrive\text{-}P^3} progressively generates CoT reasoning and answers for perception, prediction, and planning, where perception provides essential information for subsequent prediction and planning, while both perception and prediction collectively contribute to the final planning decisions, enabling safer and more interpretable autonomous driving. Additionally, to balance inference efficiency with performance, we introduce dual thinking modes: detailed thinking and fast thinking. Extensive experiments on both open-loop (nuScenes) and closed-loop (NAVSIMv1/v2) benchmarks demonstrate that our approach achieves state-of-the-art performance in planning tasks. Code is available at https://github.com/haha-yuki-haha/AutoDrive-P3.

Yuqi Ye, Zijian Zhang, Junhong Lin +3

School of Electronic and Computer Engineering, Peking University

Autonomous Driving PlanningVLMs for Autonomous DrivingRL for VLMsAutonomous Driving Perception
AskPDF
Mar 29, 2026

TIR-Agent: Training an Explorative and Efficient Agent for Image Restoration

Vision-language agents that orchestrate specialized tools for image restoration (IR) have emerged as a promising method, yet most existing frameworks operate in a training-free manner. They rely on heuristic task scheduling and exhaustive tool traversal, resulting in sub-optimal restoration paths and prohibitive computational cost. We argue that the core bottleneck lies in the absence of a learned policy to make decision, as a vision-language model cannot efficiently handle degradation-aware task ordering and tool composition. To this end, we propose TIR-Agent, a trainable image restoration agent that performs a direct tool-calling policy through a two-stage training pipeline of supervised fine-tuning (SFT) followed by reinforcement learning (RL). Two key designs underpin effective RL training: (i) a random perturbation strategy applied to the SFT data, which broadens the policy's exploration over task schedules and tool compositions, and (ii) a multi-dimensional adaptive reward mechanism that dynamically re-weights heterogeneous image quality metrics to mitigate reward hacking. To support high-throughput, asynchronous GPU-based tool invocation during training, we further develop a globally shared model-call pool. Experiments on both in-domain and out-of-domain degradations show that TIR-Agent outperforms 12 baselines, including 6 all-in-one models, 3 training-free agents, and 3 proprietary models, and achieves over 2.5×\times inference speedup by eliminating redundant tool executions.

Guoli Jia, Yisheng Zhang, Haote Hu +11

Tsinghua University, Beijing, China · Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China · Hunan University, Changsha, China +2

Tool-Using Vision-Language AgentsImage RestorationRL for VLMsAgent-Based Image Restoration
AskPDF
Mar 29, 2026

LVRPO: Language-Visual Alignment with GRPO for Multimodal Understanding and Generation

Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision within a single foundation model. However, existing approaches largely rely on implicit or indirect alignment signals and remain suboptimal for simultaneously supporting multimodal understanding and generation, particularly in settings that require fine-grained language-visual reasoning and controllable generation. In this work, we propose LVRPO, a language-visual reinforcement-based preference optimization framework that explicitly aligns language and visual representations using Group Relative Policy Optimization (GRPO). Instead of introducing additional alignment losses at the representation level, LVRPO directly optimizes multimodal model behaviors through preference-driven reinforcement signals, encouraging consistent and semantically grounded interactions between language and vision across both understanding and generation tasks. This formulation enables effective alignment without requiring auxiliary encoders or handcrafted cross-modal objectives, and naturally extends to diverse multimodal capabilities. Empirically, LVRPO consistently outperforms strong unified-pretraining baselines on a broad suite of benchmarks spanning multimodal understanding, generation, and reasoning.

Shentong Mo, Sukmin Yun

Department of Machine Learning, CMU, USA · Department of Machine Learning, MBZUAI, UAE · Department of Artificial Intelligence, Hanyang University ERICA, South Korea

Vision-Language AlignmentUnified Multimodal ModelsMultimodal UnderstandingMultimodal GenerationRL for VLMs
AskPDF
Mar 29, 2026

Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

To enhance the perception and reasoning capabilities of multimodal large language models in complex visual scenes, recent research has introduced agent-based workflows. In these works, MLLMs autonomously utilize image cropping tool to analyze regions of interest for question answering. While existing training strategies, such as those employing supervised fine-tuning and reinforcement learning, have made significant progress, our empirical analysis reveals a key limitation. We demonstrate the model's strong reliance on global input and its weak dependence on the details within the cropped region. To address this issue, we propose a novel two-stage reinforcement learning framework that does not require trajectory supervision. In the first stage, we introduce the ``Information Gap" mechanism by adjusting the granularity of the global image. This mechanism trains the model to answer questions by focusing on cropped key regions, driven by the information gain these regions provide. The second stage further enhances cropping precision by incorporating a grounding loss, using a small number of bounding box annotations. Experiments show that our method significantly enhances the model's attention to cropped regions, enabling it to achieve state-of-the-art performance on high-resolution visual question-answering benchmarks. Our method provides a more efficient approach for perceiving and reasoning fine-grained details in MLLMs. Code is available at: https://github.com/XuanPu-Z/LFPC.

Xuanpu Zhao, Zhentao Tan, Dianmo Sheng +6

School of Cyber Science and Technology, University of Science and Technology of China · Anhui Province Key Laboratory of Digital Security · Independent Researcher

Visual Question AnsweringRL for VLMsFine-Grained Visual PerceptionVisual Attention
AskPDF
Mar 29, 2026

Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the linkage between visual evidence and intermediate steps and often causing unstable optimization and visual hallucinations. We propose Differential Feedback, which automatically constructs token/step-level supervision masks by repairing erroneous reasoning trajectories, explicitly marking the key positions that require correction. Without costly large-scale step-by-step human annotations, our method enables process-level visual alignment and can be seamlessly integrated into existing GRPO-like frameworks. Experiments on multimodal reasoning benchmarks including MMMStar and MathVista show an average 3% improvement under matched compute budgets. Our approach offers an effective, low-cost solution for accurate vision--reasoning process alignment.

Feiding, Yongkang Zhang, Yuhao Liao +10

Shenzhen International Graduate School, Tsinghua University, China

RL for VLMsReasoning for VLMsVLM ReasoningVision-Language Alignment
AskPDF
Mar 28, 2026

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models

Reinforcement Learning from Verifiable Rewards (RLVR) has substantially enhanced the reasoning capabilities of large language models in abstract reasoning tasks. However, its application to Large Vision-Language Models (LVLMs) remains constrained by a structural representational bottleneck. Existing approaches generally lack explicit modeling and effective utilization of visual information, preventing visual representations from being tightly coupled with the reinforcement learning optimization process and thereby limiting further improvements in multimodal reasoning performance. To address this limitation, we propose KAWHI (Key-Region Aligned Weighted Harmonic Incentive), a plug-and-play reward reweighting mechanism that explicitly incorporates structured visual information into uniform reward policy optimization methods (e.g., GRPO and GSPO). The method adaptively localizes semantically salient regions through hierarchical geometric aggregation, identifies vision-critical attention heads via structured attribution, and performs paragraph-level credit reallocation to align spatial visual evidence with semantically decisive reasoning steps. Extensive empirical evaluations on diverse reasoning benchmarks substantiate KAWHI as a general-purpose enhancement module, consistently improving the performance of various uniform reward optimization methods. Project page: KAWHI (https://kawhiiiileo.github.io/KAWHI_PAGE/)

Yuhang Han, Yuyang Wu, Zhengbo Jiao +6

EPIC Lab, SJTU · HKUST (GZ) · Huawei

VLM ReasoningRL for VLMsLarge Vision-Language ModelsReinforcement Learning with Verifiable RewardsReward Shaping
AskPDF
Mar 28, 2026

Incentivizing Temporal-Awareness in Egocentric Video Understanding Models

Multimodal large language models (MLLMs) have recently shown strong performance in visual understanding, yet they often lack temporal awareness, particularly in egocentric settings where reasoning depends on the correct ordering and evolution of events. This deficiency stems in part from training objectives that fail to explicitly reward temporal reasoning and instead rely on frame-level spatial shortcuts. To address this limitation, we propose Temporal Global Policy Optimization (TGPO), a reinforcement learning with verifiable rewards (RLVR) algorithm designed to incentivize temporal awareness in MLLMs. TGPO contrasts model outputs generated from temporally ordered versus shuffled video frames to derive calibrated, globally normalized reward signals that explicitly favor temporally coherent reasoning. Integrated with GRPO and GSPO, TGPO supports cold-start RL training and effectively suppresses spatial shortcut behaviors learned by existing MLLMs. Experiments across five egocentric video benchmarks demonstrate that TGPO consistently improves temporal grounding and causal coherence, outperforming prior RL-based video reasoning approaches. Our results suggest that TGPO offers a simple and scalable pathway toward temporally robust MLLMs for egocentric video understanding.

Zhiyang Xu, Tian Qin, Bowen Jin +4

Virginia Tech · Harvard University · UIUC +2

Egocentric Video UnderstandingRL for VLMsTemporal Video GroundingReinforcement Learning with Verifiable Rewards
AskPDF
Mar 27, 2026

VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation

Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance during deployment. However, standard offline Supervised Fine-Tuning (SFT) suffers from distribution shifts and catastrophic forgetting of pre-trained capabilities, while online Reinforcement Learning (RL) struggles with sparse rewards and poor sample efficiency. In this paper, we propose On-Policy VLA Distillation (VLA-OPD), a framework bridging the efficiency of SFT with the robustness of RL. Instead of relying on sparse environmental rewards, VLA-OPD leverages an expert teacher to provide dense, token-level supervision on the student's self-generated trajectories. This enables active error correction on policy-induced states while preserving pre-trained general capabilities through gentle alignment. Crucially, we formulate VLA-OPD via a Reverse-KL objective. Unlike standard Forward-KL that induces mode-covering entropy explosion, or Hard-CE that causes premature entropy collapse, our bounded mode-seeking objective ensures stable policy learning by filtering out the teacher's epistemic uncertainty while maintaining action diversity. Experiments on LIBERO and RoboTwin2.0 benchmarks demonstrate that VLA-OPD significantly improves sample efficiency over RL and robustness over SFT, while effectively mitigating catastrophic forgetting during post-training.

Zhide Zhong, Haodong Yan, Junfeng Li +3

HKUST (GZ)

Vision-Language-Action ModelsOn-Policy DistillationRL for VLMs
AskPDF
Mar 27, 2026

Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and strengthening visual grounding. However, a critical bottleneck remains: although models can attend to relevant visual regions, they often fail to effectively incorporate visual evidence into subsequent reasoning, leading to reasoning chains that are weakly grounded in visual facts. To address this issue, we propose Trajectory-Guided Reinforcement Learning (TGRL), which guides the policy model to integrate visual evidence into fine-grained reasoning processes using expert reasoning trajectories from stronger models. We further introduce token-level reweighting and trajectory filtering to ensure stable and effective policy optimization. Extensive experiments on multiple multimodal reasoning benchmarks demonstrate that TGRL consistently improves reasoning performance and effectively bridges the gap between visual perception and logical reasoning.

Jinda Lu, Junkang Wu, Jinghan Li +6

University of Science and Technology of China · Pecking University · Institute of Software, Chinese Academy of Sciences

RL for VLMsMultimodal ReasoningVisually Grounded ReasoningReinforcement Learning with Verifiable RewardsLLM-Guided RL
AskPDF
Mar 26, 2026

Reinforcing Structured Chain-of-Thought for Video Understanding

Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when enhanced by Reinforcement Learning (RL) techniques like Group Relative Policy Optimization (GRPO). Moreover, existing RL methods usually depend on Supervised Fine-Tuning (SFT), which requires costly Chain-of-Thought (CoT) annotation and multi-stage training, and enforces fixed reasoning paths, limiting MLLMs' ability to generalize and potentially inducing bias. To overcome these limitations, we introduce Summary-Driven Reinforcement Learning (SDRL), a novel single-stage RL framework that obviates the need for SFT by utilizing a Structured CoT format: Summarize -> Think -> Answer. SDRL introduces two self-supervised mechanisms integrated into the GRPO objective: 1) Consistency of Vision Knowledge (CVK) enforces factual grounding by reducing KL divergence among generated summaries; and 2) Dynamic Variety of Reasoning (DVR) promotes exploration by dynamically modulating thinking diversity based on group accuracy. This novel integration effectively balances alignment and exploration, supervising both the final answer and the reasoning process. Our method achieves state-of-the-art performance on seven public VideoQA datasets.

Peiyao Wang, Haotian Xu, Noranart Vesdapunt +6

Stony Brook University · Amazon

Structured CoT ReasoningRL for VLMsReinforcement LearningVideo QACoT ReasoningTemporal Video Understanding
AskPDF
Mar 26, 2026

Pixelis: Reasoning in Pixels, from Seeing to Acting

Most vision-language systems are static observers: they describe pixels, do not act, and cannot safely improve under shift. This passivity limits generalizable, physically grounded visual intelligence. Learning through action, not static description, is essential beyond curated data. We present Pixelis, a pixel-space agent that operates directly on images and videos via a compact set of executable operations (zoom/crop, segment, track, OCR, temporal localization) and learns from its consequences. Pixelis trains in three phases: (1) Supervised Fine-Tuning learns a pixel-tool grammar from Chain-of-Thought-Action traces with a masked imitation loss that upweights operation/argument tokens and auxiliary heads to stabilize pixel-grounded arguments; (2) Curiosity-Coherence Reward Fine-Tuning optimizes a dual-drive objective marrying prediction-error curiosity with adjacent-step coherence and a mild efficiency prior under a KL anchor, yielding short, valid, structured toolchains; (3) Pixel Test-Time RL performs label-free adaptation by retrieving neighbors, voting over complete trajectories rather than answers, and updating toward short, high-fidelity exemplars while constraining drift with a KL-to-EMA safety control. Across six public image and video benchmarks, Pixelis yields consistent improvements: the average relative gain is +4.08% over the same 8B baseline (peaking at +6.03% on VSI-Bench), computed as (ours-baseline)/baseline, while producing shorter, auditable toolchains and maintaining in-corridor KL during test-time learning. Acting within pixels, rather than abstract tokens, grounds multimodal perception in the physical world, linking visual reasoning with actionable outcomes, and enables embodied adaptation without external feedback.

Yunpeng Zhou

University of Reading, Reading, UK

Tool Use in VLMsVisual ReasoningRL for VLMsTest-Time Adaptation of VLMsVideo Reasoning
AskPDF
Mar 26, 2026

Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs

Extending Reinforcement Learning with Verifiable Rewards (RLVR) to multimodal large language models (MLLMs) faces a fundamental challenge: their responses inherently interleave perception-related tokens, which ground visual content, with reasoning-related tokens, which construct reasoning chains. These token types instantiate distinct yet interdependent capacities -- visual grounding and symbolic reasoning -- making isolated optimization insufficient. Through token-level empirical analysis, we demonstrate that optimizing either perception- or reasoning-only tokens consistently underperforms full optimization, underscoring their inherent coupling. To address this, we propose a plug-and-play Token-Reweighting (ToR) strategy that explicitly models this interdependence by identifying critical tokens of both types and dynamically reweighting them during RLVR training. Applied on top of existing methods (e.g., GRPO and DAPO), ToR delivers consistent performance gains across multiple multi-modal reasoning benchmarks, achieving state-of-the-art performance with both accurate visual grounding and coherent reasoning.

Jinda Lu, Junkang Wu, Jinghan Li +6

University of Science and Technology of China · Peking University · Independent Researcher

RL for VLMsVLM ReasoningMultimodal Large Language ModelsReinforcement Learning with Verifiable Rewards
AskPDF
Mar 26, 2026

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual tokens. Observing that MLLMs handle short visual inputs well, recent LVU works alleviate hallucinations by automatically parsing the vast visual data into manageable segments that can be effectively processed by MLLMs. SFT-based tool-calling methods can serve this purpose, but they typically require vast amounts of fine-grained, high-quality data and suffer from constrained tool-calling trajectories. We propose a novel VideoTIR that leverages Reinforcement Learning (RL) to encourage proper usage of comprehensive multi-level toolkits for efficient long video understanding. VideoTIR explores both Zero-RL and SFT cold-starting to enable MLLMs to retrieve and focus on meaningful video segments/images/regions, enhancing long video understanding both accurately and efficiently. To reduce redundant tool-calling, we propose Toolkit Action Grouped Policy Optimization (TAGPO), which enhances the efficiency of the calling process through stepwise reward assignment and reuse of failed rollouts. Additionally, we develop a sandbox-based trajectory synthesis framework to generate high-quality trajectories data. Extensive experiments on three long-video QA benchmarks demonstrate the effectiveness and efficiency of our method.

Zhe Gao, Shiyu Shen, Taifeng Chai +7

Nanjing University, Nanjing, China · Nankai University, Tianjin, China · East China Normal University, Shanghai, China +3

Tool Use in VLMsEfficient VLM InferenceLong-Video UnderstandingLong-Video QARL for VLMs
AskPDF
Mar 26, 2026

MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm has recently been extended to Vision-Language Models (VLMs), enabling scalable multi-modal understanding with reduced computational cost. However, the widely adopted deterministic top-K routing mechanism may overlook more optimal expert combinations and lead to expert overfitting. To address this limitation and improve the diversity of expert selection, we propose MoE-GRPO, a reinforcement learning (RL)-based framework for optimizing expert routing in MoE-based VLMs. Specifically, we formulate expert selection as a sequential decision-making problem and optimize it using Group Relative Policy Optimization (GRPO), allowing the model to learn adaptive expert routing policies through exploration and reward-based feedback. Furthermore, we introduce a modality-aware router guidance that enhances training stability and efficiency by discouraging the router from exploring experts that are infrequently activated for a given modality. Extensive experiments on multi-modal image and video benchmarks show that MoE-GRPO consistently outperforms standard top-K routing and its variants by promoting more diverse expert selection, thereby mitigating expert overfitting and enabling a task-level expert specialization.

Dohwan Ko, Jinyoung Park, Seoung Choi +3

Korea University · KAIST

Expert RoutingMixture-of-Experts ModelsRL for VLMs
AskPDF
Mar 24, 2026

Learning to Select Visual In-Context Demonstrations

Multimodal Large Language Models (MLLMs) adapt to visual tasks via in-context learning (ICL), which relies heavily on demonstration quality. The dominant demonstration selection strategy is unsupervised k-Nearest Neighbor (kNN) search. While simple, this similarity-first approach is sub-optimal for complex factual regression tasks; it selects redundant examples that fail to capture the task's full output range. We reframe selection as a sequential decision-making problem and introduce Learning to Select Demonstrations (LSD), training a Reinforcement Learning agent to construct optimal demonstration sets. Using a Dueling DQN with a query-centric Transformer Decoder, our agent learns a policy that maximizes MLLM downstream performance. Evaluating across five visual regression benchmarks, we uncover a crucial dichotomy: while kNN remains optimal for subjective preference tasks, LSD significantly outperforms baselines on objective, factual regression tasks. By balancing visual relevance with diversity, LSD better defines regression boundaries, illuminating when learned selection is strictly necessary for visual ICL.

Eugene Lee, Yu-Chi Lin, Jiajie Diao

University of Cincinnati · University of California, Los Angeles

In-Context Example SelectionMultimodal ICLRL for VLMs
AskPDF
Mar 22, 2026

RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1% of the data, RoboAlign achieves performance improvements of 17.5%, 18.9%, and 106.6% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.

Dongyoung Kim, Sumin Park, Woomin Song +6

KAIST · RLWRLD · Yonsei University +1

Vision-Language-Action ModelsReasoning for VLA ModelsModality Gap in VLMsRL for VLMs
AskPDF