RL for VLMs

Visual question answering increasingly requires multi-step reasoning. Recent post-training with reinforcement learning under verifiable rewards (RLVR) and Group Relative Policy Optimization (GRPO) can improve multimodal reasoning, but most approaches rely on sparse outcome-only rewards. As a result, they struggle to tell whether an incorrect answer comes from a small mistake late in the reasoning or from an unhelpful trajectory from the start. A common solution is to train a process reward model (PRM) for step-level supervision, but this typically requires large-scale high-quality chain-of-thought annotations and additional training cost. We propose ProcessThinker, a practical post-training pipeline that provides step-level process rewards without training an explicit PRM. ProcessThinker first rewrites reasoning traces into a step-tagged format for cold-start supervised fine-tuning, then applies GRPO with a standard format reward and our rollout-based process reward. Concretely, for each intermediate step, we sample multiple continuations from that step and use the empirical success rate (final-answer verification) as the step reward. This gives dense credit assignment and encourages reasoning steps that more reliably support a correct conclusion, helping reduce inconsistent or self-contradictory progress across steps -- a key issue in logical reasoning. Across four challenging video benchmarks (Video-MMMU, MMVU, VideoMathQA, and LongVideoBench), ProcessThinker consistently improves over the baseline model Qwen3-VL-8B-Instruct

There are 7,407 languages in the world. But, what about the languages that are not there in the world? Are humans so narrow minded that we don't care about the languages aliens communicate in? Aliens are humans too! In the 2016 movie Arrival, Amy Adams plays a linguist, Dr. Louise Banks who, by learning to think in an alien language (Heptapod) formed of non-sequential sentences, gains the ability to transcend time and look into the future. In this work, I aim to explore the representation and reasoning of vision-language concepts in a neuro-symbolic language, and study improvement in analytical reasoning abilities and efficiency of "thinking systems". With Qwen3-VL-2B-Instruct as base model and 4 $\times$ Nvidia H200 GPU nodes, I achieve an accuracy improvement of 3.33% on a vision-language evaluation dataset consisting of math, science, and general knowledge questions, while reducing the reasoning tokens by 75% over SymPy. I've documented the compute challenges faced, scaling possibilities, and the future work to improve thinking in a neuro-symbolic language in vision-language models. The training and inference setup can be found here: https://github.com/i-like-bfs-and-dfs/wolfram-reasoning.

Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucination where predicted 3D structures contradict the observed 2D reality. We identify a key cause of this failure not as a representation bottleneck but as a structural misalignment in reinforcement learning, where sparse geometric tokens are drowned out by noisy and broadcasted sequence-level rewards. To resolve this causal dilution, we propose Geometric Reward Credit Assignment, a framework that disentangles holistic supervision into field-specific signals and routes them exclusively to their responsible token spans. This mechanism transforms vague feedback into precise gradient updates and effectively turns generic policy optimization into targeted structural alignment. Furthermore, we internalize physical constraints via a Reprojection-Consistency term which serves as a cross-modal verifier to penalize physically impossible geometries. Validated on a calibrated benchmark derived from ShapeNetCore, our approach bridges the reliability gap by boosting 3D KPA from 0.64 to 0.93, increasing 3D bounding box intersection over union to 0.686, and raising reprojection consistency scores to 0.852. Crucially, these gains are achieved while maintaining robust 2D localization performance, marking a meaningful step from plausible textual outputs toward physically verifiable spatial predictions.

We introduce V-tableR1, a process-supervised reinforcement learning framework that elicits rigorous, verifiable reasoning from multimodal large language models (MLLMs). Current MLLMs trained solely on final outcomes often treat visual reasoning as a black box, relying on superficial pattern matching rather than performing rigorous multi-step inference. While Reinforcement Learning with Verifiable Rewards could enforce transparent reasoning trajectories, extending it to visual domains remains severely hindered by the ambiguity of grounding abstract logic into continuous pixel space. We solve this by leveraging the deterministic grid structure of tables as an ideal visual testbed. V-tableR1 employs a specialized critic VLM to provide dense, step-level feedback on the explicit visual chain-of-thought generated by a policy VLM. To optimize this system, we propose Process-Guided Direct Alignment Policy Optimization (PGPO), a novel RL algorithm integrating process rewards, decoupled policy constraints, and length-aware dynamic sampling. Extensive evaluations demonstrate that V-tableR1 explicitly penalizes visual hallucinations and shortcut guessing. By fundamentally shifting multimodal inference from black-box pattern matching to verifiable logical derivation, V-tableR1 4B establishes state-of-the-art accuracy among open-source models on complex tabular benchmarks, outperforming models up to 18x its size and improving over its SFT baseline

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive manual annotations prevents MLLMs' intrinsic visual understanding and scalable reward designs. In this work, we introduce SSL-R1, a generic self-supervised RL framework that derives verifiable rewards directly from images. To this end, we revisit self-supervised learning (SSL) in visual domains and reformulate widely-used SSL tasks into a set of verifiable visual puzzles for RL post-training, requiring neither human nor external model supervision. Training MLLMs on these tasks substantially improves their performance on multimodal understanding and reasoning benchmarks, highlighting the potential of leveraging vision-centric self-supervised tasks for MLLM post-training. We think this work will provide useful experience in devising effective self-supervised verifiable rewards to enable RL at scale. Project page: https://github.com/Jiahao000/SSL-R1.

Training multimodal agents via reinforcement learning for knowledge-intensive visual reasoning is fundamentally hindered by the extreme sparsity of outcome-based supervision and the unpredictability of live web environments. To resolve these algorithmic and environmental bottlenecks, we introduce ProMMSearchAgent, establishing a novel Sim-to-Real training paradigm for multimodal search. We decouple policy learning into a deterministic, local static sandbox. Crucially, to learn effectively within this constrained environment, we propose an introspective process-oriented reward. By probing the agent's own parametric knowledge boundaries, we generate dense behavioral metadata that explicitly rewards the correct cognitive decision, initiating a multimodal or text search only when visually or factually uncertain. Extensive experiments demonstrate that our locally-trained policy transfers zero-shot to the live Google Search API. ProMMSearchAgent achieves new SOTA performance, outperforming MMSearch-R1 by +5.1% on FVQA-test, +6.3% on InfoSeek, and +11.3% on MMSearch.

Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on the pretrained inherent reasoning rationales whilst lacking perception-aware adaptation to the input video content. To address this, we propose Video-ToC, a novel video reasoning framework that enhances video understanding through tree-of-cue reasoning. Specifically, our approach introduces three key innovations: (1) A tree-guided visual cue localization mechanism, which endows the model with enhanced fine-grained perceptual capabilities through structured reasoning patterns; (2) A reasoning-demand reward mechanism, which dynamically adjusts the reward value for reinforcement learning (RL) based on the estimation of reasoning demands, enabling on-demand incentives for more effective reasoning strategies; and (3) An automated annotation pipeline that constructs the Video-ToC-SFT-1k and Video-ToC-RL-2k datasets for supervised fine-tuning (SFT) and RL training, respectively. Extensive evaluations on six video understanding benchmarks and a video hallucination benchmark demonstrate the superiority of Video-ToC over baselines and recent methods. Code is available at https://github.com/qizhongtan/Video-ToC.

Chain-of-Thought (CoT) reasoning significantly elevates the complex problem-solving capabilities of multimodal large language models (MLLMs). However, adapting CoT to vision typically discretizes signals to fit LLM inputs, causing early semantic collapse and discarding fine-grained details. While external tools can mitigate this, they introduce a rigid bottleneck, confining reasoning to predefined operations. Although recent latent reasoning paradigms internalize visual states to overcome these limitations, optimizing the resulting hybrid discrete-continuous action space remains challenging. In this work, we propose HyLaR (Hybrid Latent Reasoning), a framework that seamlessly interleaves discrete text generation with continuous visual latent representations. Specifically, following an initial cold-start supervised fine-tuning (SFT), we introduce DePO (Decoupled Policy Optimization) to enable effective reinforcement learning within this hybrid space. DePO decomposes the policy gradient objective, applying independent trust-region constraints to the textual and latent components, alongside an exact closed-form von Mises-Fisher (vMF) KL regularizer. Extensive experiments demonstrate that HyLaR outperforms standard MLLMs and state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks. Code is available at https://github.com/EthenCheng/HyLaR.

In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Models. To achieve that, we propose a novel Tool-supervised Reinforcement Learning (ToolsRL) framework, with direct tool supervision for more effective tool-use learning. We focus on a series of simple, native, and interpretable visual tools, including zoom-in, rotate, flip, and draw point/line, whose tool supervision is easy to collect. A reinforcement learning curriculum is developed, where the first stage is solely optimized by a set of well motivated tool-specific rewards, and the second stage is trained with the accuracy targeted rewards while allowing calling tools. In this way, tool calling capability is mastered before using tools to complete visual reasoning tasks, avoiding the potential optimization conflict among those heterogeneous tasks. Our experiments have shown that the tool-supervised curriculum training is efficient and ToolsRL can achieve strong tool-use capabilities for complex visual reasoning tasks.

Reinforcement fine-tuning with verifiable rewards (RLVR) has emerged as a powerful paradigm for equipping large vision-language models (LVLMs) with agentic capabilities such as tool use and multi-step reasoning. Despite striking empirical successes, most notably Visual Agentic Reinforcement Fine-Tuning (Visual-ARFT), the theoretical underpinnings of this paradigm remain poorly understood. In particular, two critical questions lack rigorous answers: (i)how does the composite structure of verifiable rewards (format compliance, answer accuracy, tool executability) affect the convergence of Group Relative Policy Optimization (GRPO), and (ii)why does training on a small set of tool-augmented tasks transfer to out-of-distribution domains? We address these gaps by introducing the Tool-Augmented Markov Decision Process (TA-MDP), a formal framework that models multimodal agentic decision-making with bounded-depth tool calls. Within this framework, we establish three main results. First, we prove that GRPO under composite verifiable rewards converges to a first-order stationary point at rate $O(1/\sqrt{T})$ with explicit dependence on the number of reward components and group size (**Theorem1**). Second, we derive a Reward Decomposition Theorem that bounds the sub-optimality gap between decomposed per-component optimization and joint optimization, providing a precise characterization of when reward decomposition is beneficial (**Theorem2**). Third, we establish a PAC-Bayes generalization bound for tool-augmented policies that explains the strong out-of-distribution transfer observed in Visual-ARFT (Theorem~3).

Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However, their capacity for visual semantic arithmetic, inferring relationships from images, remains underexplored. The classic text analogy "king"-"man"+"woman" = "queen" illustrates relational reasoning, yet replacing text with images of "king" and "man" significantly reduces performance because it requires commonsense knowledge and the extraction of concise concepts from irrelevant visual details. This capability is important for service and domestic robotics in unstructured environments, where robots must infer semantic relationships among objects, agents, and actions. In a kitchen, recognizing from images that "powder" and "cake" are related by "is made of" grounds symbolic relations in perception, enabling tool substitution, task generalization, and improved semantic reasoning. Prior work approaches semantic arithmetic by decoding image features after vector arithmetic, but suffers from modality gaps and lacks systematic evaluation. In this paper, we formulate two novel tasks, two-term subtraction and three-term operations, and construct the Image-Relation-Pair Dataset (IRPD) for benchmarking. We further propose Semantic Arithmetic Reinforcement Fine-Tuning (SAri-RFT), which post-trains large vision-language models (LVLMs) using a verifiable function and Group Relative Policy Optimization (GRPO). Our method achieves state-of-the-art results on IRPD and the real-world Visual7W-Telling dataset. By equipping LVLMs with robust cross-modal relational reasoning, this work advances domestic robots' ability to ground symbolic reasoning in perception, enhancing decision-making, tool adaptability, and human-robot interaction in complex environments. Datasets and source code are provided in the supplementary material.

Self-evolution of multimodal large language models (MLLMs) remains a critical challenge: pseudo-label-based methods suffer from progressive quality degradation as model predictions drift, while template-based methods are confined to a static set of transformations that cannot adapt in difficulty or diversity. We contend that robust, continuous self-improvement requires not only deterministic external feedback independent of the model's internal certainty, but also a mechanism to perpetually diversify the training distribution. To this end, we introduce EVE (Executable Visual transformation-based self-Evolution), a novel framework that entirely bypasses pseudo-labels by harnessing executable visual transformations continuously enriched in both variety and complexity. EVE adopts a Challenger-Solver dual-policy architecture. The Challenger maintains and progressively expands a queue of visual transformation code examples, from which it synthesizes novel Python scripts to perform dynamic visual transformations. Executing these scripts yields VQA problems with absolute, execution-verified ground-truth answers, eliminating any reliance on model-generated supervision. A multi-dimensional reward system integrating semantic diversity and dynamic difficulty calibration steers the Challenger to enrich its code example queue while posing progressively more challenging tasks, preventing mode collapse and fostering reciprocal co-evolution between the two policies. Extensive experiments demonstrate that EVE consistently surpasses existing self-evolution methods, establishing a robust and scalable paradigm for verifiable MLLM self-evolution. The code is available at https://github.com/0001Henry/EVE .

Reinforcement learning (RL) post-training substantially improves remote sensing vision-language models (RS-VLMs). However, when handling complex remote sensing imagery (RSI) requiring exhaustive visual scanning, models tend to rely on localized salient cues for rapid inference. We term this RL-induced bias "perceptual inertia". Driven by reward maximization, models favor quick outcome fitting, leading to two limitations: cognitively, overreliance on specific features impedes complete evidence construction; operationally, models struggle to flexibly shift visual focus across tasks. To address this bias and encourage comprehensive visual evidence mining, we propose RS-HyRe-R1, a hybrid reward framework for RSI understanding. It introduces: (1) a spatial reasoning activation reward that enforces structured visual reasoning; (2) a perception correctness reward that provides adaptive quality anchors across RS tasks, ensuring accurate geometric and semantic alignment; and (3) a visual-semantic path evolution reward that penalizes repetitive reasoning and promotes exploration of complementary cues to build richer evidence chains. Experiments show RS-HyRe-R1 effectively mitigates "perceptual inertia", encouraging deeper, more diverse reasoning. With only 3B parameters, it achieves state-of-the-art performance on REC, OVD, and VQA tasks, outperforming models up to 7B parameters. It also demonstrates strong zero-shot generalization, surpassing the second-best model by 3.16%, 3.97%, and 2.72% on VQA, OVD, and REC, respectively. Code and datasets are available at https://github.com/geox-lab/RS-HyRe-R1.

Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration. They typically require expensive supervised trajectory tuning to mitigate these deficits. In this work, we propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA), a supervision-free framework that bootstraps agentic capabilities via Coldstart Reinforcement Learning for SVLMs. SPECTRA enforces Soft Structured Multi-turn Rollouts, a topological constraint that directs agents to explicitly sequence tool derived evidence before synthesis, effectively grounding reasoning in visual observations. We employ a multi-objective reward signal that simultaneously maximizes task correctness, rollout structure, and tool utility, enabling agent to self-discover robust behaviors without human preference labels. We further introduce Tool Instrumental Utility (TIU), a novel metric to quantify tool efficacy in the absence of ground truth. Extensive evaluations across composite and out-of-distribution (MMMU-Pro) benchmarks demonstrate that SPECTRA boosts agentic trajectories, improving task accuracy by up to 5% and tool efficiency by 9%, enabling more efficient multimodal agents that learn effectively from environmental interaction alone.

Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm. However, these methods discard all collected trajectories after a single gradient update, resulting in poor sample efficiency, particularly wasteful for agentic tasks where multi-turn environment interactions are expensive. While Experience Replay drives sample efficiency in classic RL by allowing agents to reuse past trajectories and prioritize informative ones, directly applying Prioritized Experience Replay (PER) to LLMs fails. The rapid policy evolution of billion-parameter models renders stored priorities stale, causing old high-priority trajectories to dominate sampling long after they have become uninformative. We propose Freshness-Aware PER, which addresses this priority staleness problem by augmenting any PER-based priority with a multiplicative exponential age decay grounded in effective sample size analysis. To the best of our knowledge, Freshness-Aware PER is the first work to successfully apply PER to LLM/VLM reinforcement learning. We evaluate on eight multi-step agentic, reasoning, and math competition tasks with 0.5B, 3B, and 7B models. Freshness-Aware PER significantly outperforms on-policy baselines, achieving +46% on NQ Search, +367% on Sokoban, and +133% on VLM FrozenLake, while standard PER without age decay consistently degrades performance. Our code is publicly available at https://github.com/Vision-CAIR/Freshness-Aware-PER.

Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve into natively multimodal architectures, extending RLVR to video understanding becomes increasingly important yet remains largely unexplored, due to the diversity of video task types, the computational overhead of repeatedly decoding and preprocessing high-dimensional visual inputs, and the difficulty of reproducible evaluation across numerous sensitive hyperparameters. Existing open-source RL training frameworks provide solid infrastructure for text and image scenarios but lack systematic optimizations tailored for video modality. In this work, we present EasyVideoR1, a complete and efficient reinforcement learning framework specifically designed for training large vision-language models on video understanding tasks. EasyVideoR1 makes the following contributions: (1) a full video RL training pipeline with offline preprocessing and tensor caching that eliminates redundant video decoding and yields a 1.47 $\times$ throughput improvement; (2) a comprehensive, task-aware reward system covering 11 distinct video and image problem types with unified routing and modular extension; (3) a mixed offline-online data training paradigm that combines curated high-quality trajectories with on-policy exploration, benefiting the learning of more challenging tasks; (4) joint image-video training with independently configurable pixel budgets, allowing the two modalities to mutually reinforce each other; and (5) an asynchronous multi-benchmark evaluation framework covering 22 mainstream video understanding benchmarks, with reproduced accuracy closely aligned with officially reported scores.

Image Quality Assessment (IQA) models are increasingly deployed as perceptual critics to guide generative models and image restoration. This role demands not only accurate scores but also actionable, localized feedback. However, current MLLM-based methods adopt a single-look, language-only paradigm, which departs from human evidence-seeking judgment and yields weakly grounded rationales, limiting their reliability for in-the-loop refinement. We propose Q-DeepSight, a think-with-image framework that emulates this human-like process. It performs interleaved Multimodal Chain-of-Thought (iMCoT) with tool-augmented evidence acquisition (e.g., crop-and-zoom) to explicitly determine where quality degrades and why. To train these long iMCoT trajectories via reinforcement learning, we introduce two techniques: Perceptual Curriculum Reward (PCR) to mitigate reward sparsity and Evidence Gradient Filtering (EGF) to improve credit assignment for visually-grounded reasoning. Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content. Furthermore, we demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement, effectively closing the loop between assessment and refinement.

Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). Despite their prevalence, both approaches suffer from inefficiencies when applied in isolation. SFT forces the model's generation along a single expert trajectory, often inducing catastrophic forgetting of general multimodal capabilities due to distributional shifts. Conversely, RL explores multiple generated trajectories but frequently encounters optimization collapse - a cold-start problem where an unaligned model fails to spontaneously sample any domain-valid trajectories in sparse-reward visual tasks. In this paper, we propose Supervised Group Relative Policy Optimization (S-GRPO), a unified post-training framework that integrates the guidance of imitation learning into the multi-trajectory exploration of preference optimization. Tailored for direct-generation visual tasks, S-GRPO introduces Conditional Ground-Truth Trajectory Injection (CGI). When a binary verifier detects a complete exploratory failure within a sampled group of trajectories, CGI injects the verified ground-truth trajectory into the candidate pool. By assigning a deterministic maximal reward to this injected anchor, S-GRPO enforces a positive signal within the group-relative advantage estimation. This mechanism reformulates the supervised learning objective as a high-advantage component of the policy gradient, compelling the model to dynamically balance between exploiting the expert trajectory and exploring novel visual concepts. Theoretical analysis and empirical results demonstrate that S-GRPO gracefully bridges the gap between SFT and RL, drastically accelerates convergence, and achieves superior domain adaptation while preserving the base model's general-purpose capabilities.

Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge. However, existing visual RAG systems typically rely on generic retrieval signals that overlook the fine-grained visual semantics essential for complex reasoning. To address this limitation, we propose UniDoc-RL, a unified reinforcement learning framework in which an LVLM agent jointly performs retrieval, reranking, active visual perception, and reasoning. UniDoc-RL formulates visual information acquisition as a sequential decision-making problem with a hierarchical action space. Specifically, it progressively refines visual evidence from coarse-grained document retrieval to fine-grained image selection and active region cropping, allowing the model to suppress irrelevant content and attend to information-dense regions. For effective end-to-end training, we introduce a dense multi-reward scheme that provides task-aware supervision for each action. Based on Group Relative Policy Optimization (GRPO), UniDoc-RL aligns agent behavior with multiple objectives without relying on a separate value network. To support this training paradigm, we curate a comprehensive dataset of high-quality reasoning trajectories with fine-grained action annotations. Experiments on three benchmarks demonstrate that UniDoc-RL consistently surpasses state-of-the-art baselines, yielding up to 17.7% gains over prior RL-based methods.

Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO) consistently suffers from entropy collapse, causing the policy to converge prematurely and lose diversity. Existing exploration methods introduce additional bias or variance during exploration, making it difficult to maintain optimization stability. We propose Unified Entropy Control for Reinforcement Learning (UEC-RL), a framework that provides targeted mechanisms for exploration and stabilization. UEC-RL activates more exploration on difficult prompts to search for potential and valuable reasoning trajectories. In parallel, a stabilizer prevents entropy from growing uncontrollably, thereby keeping training stable as the model consolidates reliable behaviors. Together, these components expand the search space when needed while maintaining robust optimization throughout training. Experiments on both LLM and VLM reasoning tasks show consistent gains over RL baselines on both Pass@1 and Pass@$k$. On Geometry3K, UEC-RL achieves a 37.9% relative improvement over GRPO, indicating that it sustains effective exploration without compromising convergence and underscoring UEC-RL as a key for scaling RL-based reasoning in large models. Our code is available at https://github.com/597358816/UEC-RL.

Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning. However, they often suffer from overthinking, producing unnecessarily long reasoning chains for any tasks. We attribute this issue to Reasoning Path Redundancy in visual reasoning: many visual questions do not require the full reasoning process. To address this, we propose AVR, an adaptive visual reasoning framework that decomposes visual reasoning into three cognitive functions: visual perception, logical reasoning, and answer application. It further enables models to dynamically choose among three response formats: Full Format, Perception-Only Format, and Direct Answer. AVR is trained with FS-GRPO, an adaptation of Group Relative Policy Optimization that encourages the model to select the most efficient reasoning format while preserving correctness. Experiments on multiple vision-language benchmarks show that AVR reduces token usage by 50--90% while maintaining overall accuracy, especially in perception-intensive tasks. These results demonstrate that adaptive visual reasoning can effectively mitigate overthinking in VRMs. Code and data are available at: https://github.com/RunRiotComeOn/AVR.

Physical reasoning over images requires integrating perception, domain knowledge, and multi-step symbolic inference, yet Vision-Language Models (VLMs) fall far short of human performance on physics benchmarks. Reinforcement learning can improve reasoning via reward signals, but it remains unclear whether these signals must come from outside the model or can be derived from the model itself. We compare external rewards, which rely on an outside verifier (rule-based format and answer-correctness checks, or an LLM-judge rubric), with an internal attention-based reward computed from the model's own attention over image regions, requiring no labels or judge. We find that external rewards drive most of the accuracy gains, while preserving more coherent reasoning when rewarded for reasoning tokens. The internal attention-based reward, provides an annotation-free grounding signal that improves spatial-relation reasoning and is complementary to external rewards: adding it to format and accuracy rewards, at no additional annotation cost, improves average accuracy on Molmo~2 while generalizing to out-of-distribution tasks. Our results suggest that internal attention rewards can supplement external supervision and lead to improved physical reasoning.

Tables contain rich structured information, yet when stored as images their contents remain "locked" within pixels. Converting table images into LaTeX code enables faithful digitization and reuse, but current multimodal large language models (MLLMs) often fail to preserve structural, style, or content fidelity. Conventional post-training with reinforcement learning (RL) typically relies on a single aggregated reward, leading to reward ambiguity that conflates multiple behavioral aspects and hinders effective optimization. We propose Component-Specific Policy Optimization (CSPO), an RL framework that disentangles optimization across LaTeX tables components-structure, style, and content. In particular, CSPO assigns component-specific rewards and backpropagates each signal only through the tokens relevant to its component, alleviating reward ambiguity and enabling targeted component-wise optimization. To comprehensively assess performance, we introduce a set of hierarchical evaluation metrics. Extensive experiments demonstrate the effectiveness of CSPO, underscoring the importance of component-specific optimization for reliable structured generation. Our code is available at https://github.com/microsoft/CSPO.

Multimodal Large Reasoning Models (MLRMs) have achieved remarkable strides in visual reasoning through test time compute scaling, yet long chain reasoning remains prone to hallucinations. We identify a concerning phenomenon termed the Reasoning Vision Truth Disconnect (RVTD): hallucinations are strongly correlated with cognitive bifurcation points that often exhibit high entropy states. We attribute this vulnerability to a breakdown in visual semantic anchoring, localized within the network's intermediate layers; specifically, during these high uncertainty transitions, the model fails to query visual evidence, reverting instead to language priors. Consequently, we advocate a shift from solely outcome level supervision to augmenting it with fine grained internal attention guidance. To this end, we propose V-STAR (Visual Structural Training with Attention Reinforcement), a lightweight, holistic training paradigm designed to internalize visually aware reasoning capabilities. Central to our approach is the Hierarchical Visual Attention Reward (HVAR), integrated within the GRPO framework. Upon detecting high entropy states, this mechanism dynamically incentivizes visual attention across critical intermediate layers, thereby anchoring the reasoning process back to the visual input. Furthermore, we introduce the Forced Reflection Mechanism (FRM), a trajectory editing strategy that disrupts cognitive inertia by triggering reflection around high entropy cognitive bifurcation points and encouraging verification of subsequent steps against the visual input, thereby translating external debiasing interventions into an intrinsic capability for hallucination mitigation.

Reasoning capabilities are crucial for reliable medical visual question answering (VQA); however, existing datasets rarely include reasoning explanations. We address this by generating reasoning trajectories for six medical VQA benchmarks using the COMCTS algorithm with open-source vision-language models, with an LLM serving as the verification judge. Building on these generated datasets, we propose a two-stage training framework: supervised fine-tuning followed by Group Relative Policy Optimization (GRPO) with a novel process-based reward. While standard approaches rely solely on exact-match rewards for final answers, we introduce a trajectory-aware reward that measures the similarity between generated and ground-truth reasoning processes. Specifically, we embed reasoning steps using sentence transformers and compute the Dynamic Time Warping (DTW) distance between the resulting vector sequences. Experiments across six benchmarks demonstrate that combining the DTW-based process reward with exact-match reward consistently outperforms SFT-only training, raising mean accuracy from 0.598 to 0.689, mean BERTScore from 0.845 to 0.881, and mean ROUGE-L from 0.665 to 0.748. Our results highlight the importance of process supervision in training reasoning-capable medical VLMs. We make our code and generated reasoning datasets publicly available at https://anonymous.4open.science/r/MICCAI-R1-MED-VQA-code-B14B/

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence calibration methods, largely developed for text-only LLMs, typically optimize a single holistic confidence score using binary answer-level correctness. This design is mismatched to LVLMs: an incorrect prediction may arise from perceptual failures or from reasoning errors given correct perception, and a single confidence conflates these sources while visual uncertainty is often dominated by language priors. To address these issues, we propose VL-Calibration, a reinforcement learning framework that explicitly decouples confidence into visual and reasoning confidence. To supervise visual confidence without ground-truth perception labels, we introduce an intrinsic visual certainty estimation that combines (i) visual grounding measured by KL-divergence under image perturbations and (ii) internal certainty measured by token entropy. We further propose token-level advantage reweighting to focus optimization on tokens based on visual certainty, suppressing ungrounded hallucinations while preserving valid perception. Experiments on thirteen benchmarks show that VL-Calibration effectively improves calibration while boosting visual reasoning accuracy, and it generalizes to out-of-distribution benchmarks across model scales and architectures.

Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely text-centric: images are encoded once as static context, and subsequent inference is dominated by language. This paradigm is fundamentally limited in clinical scenarios, where accurate answers often depend on subtle, localized visual evidence that cannot be reliably preserved in static embeddings. We propose MedLVR, a latent visual reasoning framework that introduces an explicit visual evidence state into autoregressive decoding. Instead of relying solely on text-based intermediate reasoning, MedLVR interleaves a short latent reasoning segment within the decoder by reusing hidden states as continuous latent steps, enabling iterative preservation and refinement of query-relevant visual evidence before answer generation. To support effective visual supervision, we adopt a two-stage training strategy: region of interest (ROI)-supervised fine-tuning aligns latent states with clinically relevant image evidence, and Visual-Latent Policy Optimization (VLPO) further optimizes latent reasoning and answer generation under outcome-level rewards. Experiments on OmniMedVQA and five external medical VQA benchmarks show that MedLVR consistently outperforms recent reasoning baselines and improves the average score over the Qwen2.5-VL-7B backbone from 48.3% to 53.4%. These results show that latent visual reasoning provides an effective mechanism for preserving diagnostically relevant visual evidence and improving the reliability of medical VQA.

Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning ability of vision-language models (VLMs). However, the inherent text-dominated nature of VLMs often leads to insufficient visual faithfulness, characterized by sparse attention activation to visual tokens. More importantly, our empirical analysis reveals that temporal visual forgetting along reasoning steps exacerbates this deficiency. To bridge this gap, we propose Visually-Guided Policy Optimization (VGPO), a novel framework to reinforce visual focus during policy optimization. Specifically, VGPO initially introduces a Visual Attention Compensation mechanism that leverages visual similarity to localize and amplify visual cues, while progressively elevating visual expectations in later steps to counteract visual forgetting. Building on this mechanism, we implement a dual-grained advantage re-weighting strategy: the intra-trajectory level highlights tokens exhibiting relatively high visual activation, while the inter-trajectory level prioritizes trajectories demonstrating superior visual accumulation. Extensive experiments demonstrate that VGPO achieves better visual activation and superior performance in mathematical multimodal reasoning and visual-dependent tasks. The code has been released at https://github.com/wzb-bupt/VGPO.

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal generalist models remains heavily constrained by two primary challenges: the extreme variance in reward topologies across diverse visual tasks, and the inherent difficulty of balancing fine-grained perception with multi-step reasoning capabilities. To address these issues, we introduce Gaussian GRPO (G$^2$RPO), a novel RL training objective that replaces standard linear scaling with non-linear distributional matching. By mathematically forcing the advantage distribution of any given task to strictly converge to a standard normal distribution, $\mathcal{N}(0,1)$, G$^2$RPO theoretically ensures inter-task gradient equity, mitigates vulnerabilities to heavy-tail outliers, and offers symmetric update for positive and negative rewards. Leveraging the enhanced training stability provided by G$^2$RPO, we introduce two task-level shaping mechanisms to seamlessly balance perception and reasoning. First, response length shaping dynamically elicits extended reasoning chains for complex queries while enforce direct outputs to bolster visual grounding. Second, entropy shaping tightly bounds the model's exploration zone, effectively preventing both entropy collapse and entropy explosion. Integrating these methodologies, we present OpenVLThinkerV2, a highly robust, general-purpose multimodal model. Extensive evaluations across 18 diverse benchmarks demonstrate its superior performance over strong open-source and leading proprietary frontier models.

Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks. However, we observe that accuracy gains often come at the cost of reasoning quality: generated Chain-of-Thought (CoT) traces are frequently inconsistent with the final answer and poorly grounded in the visual evidence. We systematically study this phenomenon across seven challenging real-world spatial reasoning benchmarks and find that it affects contemporary MRMs such as ViGoRL-Spatial, TreeVGR as well as our own models trained with standard Group Relative Policy Optimization (GRPO). We characterize CoT reasoning quality along two complementary axes: "logical consistency" (does the CoT entail the final answer?) and "visual grounding" (does each reasoning step accurately describe objects, attributes, and spatial relationships in the image?). To address this, we propose Faithful GRPO (FGRPO), a variant of GRPO that enforces consistency and grounding as constraints via Lagrangian dual ascent. FGRPO incorporates batch-level consistency and grounding constraints into the advantage computation within a group, adaptively adjusting the relative importance of constraints during optimization. We evaluate FGRPO on Qwen2.5-VL-7B and 3B backbones across seven spatial datasets. Our results show that FGRPO substantially improves reasoning quality, reducing the inconsistency rate from 24.5% to 1.7% and improving visual grounding scores by +13%. It also improves final answer accuracy over simple GRPO, demonstrating that faithful reasoning enables better answers.