VLM Reasoning

Accurate and interpretable plant disease diagnosis remains a major challenge for vision-language models (VLMs) in real-world agriculture. We introduce AgriChain, a dataset of approximately 11,000 expert-curated leaf images spanning diverse crops and pathologies, each paired with (i) a disease label, (ii) a calibrated confidence score (High/Medium/Low), and (iii) an expert-verified chain-of-thought (CoT) rationale. Draft explanations were first generated by GPT-4o and then verified by a professional agricultural engineer using standardized descriptors (e.g., lesion color, margin, and distribution). We fine-tune Qwen2.5-VL-3B on AgriChain, resulting in a specialized model termed AgriChain-VL3B, to jointly predict diseases and generate visually grounded reasoning. On a 1,000-image test set, our CoT-supervised model achieves 73.1% top-1 accuracy (macro F1 = 0.466; weighted F1 = 0.655), outperforming strong baselines including Gemini 1.5 Flash, Gemini 2.5 Pro, and GPT-4o Mini. The generated explanations align closely with expert reasoning, consistently referencing key visual cues. These findings demonstrate that expert-verified reasoning supervision significantly enhances both accuracy and interpretability, bridging the gap between generic multimodal models and human expertise, and advancing trustworthy, globally deployable AI for sustainable agriculture. The dataset and code are publicly available at: https://github.com/hazzanabeel12-netizen/agrichain

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.

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either through computationally expensive post-training procedures on limited 3D datasets or through rigid tool-calling mechanisms that lack explicit geometric understanding and viewpoint flexibility. To address these challenges, we propose a training-free framework that introduces a Visual Chain-of-Thought mechanism grounded in explicit 3D reconstruction. The proposed pipeline first reconstructs a high-fidelity 3D mesh from a single image using MLLM-guided keyword extraction and mask generation at multiple granularities. Subsequently, the framework leverages an external knowledge base to iteratively compute optimal camera extrinsic parameters and synthesize novel views, thereby emulating human perspective-taking. Extensive experiments demonstrate that the proposed approach significantly enhances spatial comprehension. Specifically, the framework outperforms specialized spatial models and general-purpose MLLMs, including GPT-5.2 and Gemini-2.5-Flash, on major benchmarks such as 3DSRBench and Rel3D.

Deciphering ancient Chinese Oracle Bone Script (OBS) is a challenging task that offers insights into the beliefs, systems, and culture of the ancient era. Existing approaches treat decipherment as a closed-set image recognition problem, which fails to bridge the ``interpretation gap'': while individual characters are often unique and rare, they are composed of a limited set of recurring, pictographic components that carry transferable semantic meanings. To leverage this structural logic, we propose an agent-driven Vision-Language Model (VLM) framework that integrates a VLM for precise visual grounding with an LLM-based agent to automate a reasoning chain of component identification, graph-based knowledge retrieval, and relationship inference for linguistically accurate interpretation. To support this, we also introduce OB-Radix, an expert-annotated dataset providing structural and semantic data absent from prior corpora, comprising 1,022 character images (934 unique characters) and 1,853 fine-grained component images across 478 distinct components with verified explanations. By evaluating our system across three benchmarks of different tasks, we demonstrate that our framework yields more detailed and precise decipherments compared to baseline methods.

While Vision-Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimized for direct visual question-answering tasks. This paradigm often results in "black-box" systems that fail to utilize the inherent capability of Large Language Models (LLMs) to infer underlying reaction mechanisms. In this work, we introduce ChemVLR, a chemical VLM designed to prioritize reasoning within the perception process. Unlike conventional chemical VLMs, ChemVLR analyzes visual inputs in a fine-grained manner by explicitly identifying granular chemical descriptors, such as functional groups, prior to generating answers. This approach ensures the production of explicit and interpretable reasoning paths for complex visual chemical problems. To facilitate this methodology, we implement a cross-modality reverse-engineering strategy, combined with a rigorous filtering pipeline, to curate a large-scale reasoning-and-captioning dataset comprising 760k high-quality samples across molecular and reaction tasks. Furthermore, we adopt a three-stage training framework that systemically builds model perception and reasoning capacity. Experiments demonstrate that ChemVLR achieves state-of-the-art (SOTA) performance, surpassing both leading proprietary models and domain-specific open-source baselines. We also provide comprehensive ablation studies to validate our training strategy and data generation designs. Code and model weights will be available at https://github.com/xxlllz/ChemVLR.

Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor precise spatial localization of anomalous events. While Vision-Language Models (VLMs) offer rich scene understanding, they struggle with reliable spatial grounding - often producing hallucinated or geometrically invalid bounding boxes when asked to localize objects. We propose VANGUARD (Video Anomaly Understanding through Reasoning and Grounding), a framework that unifies anomaly classification, spatial grounding, and chain-of-thought reasoning within a single VLM. VANGUARD introduces a three-stage curriculum that progressively layers training objectives: (1) classifier warmup on frozen backbone features, (2) LoRA-adapted spatial grounding, and (3) chain-of-thought generation. To overcome the sparse annotation typical of VAD benchmarks, we employ a teacher-student annotation pipeline in which a VLM (Qwen3-VL-4B) generates structured per-subclip reasoning trajectories based on manual annotations available from the UCA Dataset. Further, GroundingDINO provides bounding box supervision. On UCF-Crime, VANGUARD achieves 94% ROC-AUC with 84% F1 while simultaneously producing interpretable chain-of-thought explanations and spatial grounding of anomalous objects - capabilities absent from prior VAD methods. Ablations confirm that staged training outperforms monolithic optimization, and that structured reasoning acts as an implicit regularizer yielding more balanced predictions than classification-only fine-tuning. Zero-shot transfer to XD-Violence and ShanghaiTech demonstrates cross-domain generalization without target-domain adaptation.

Echocardiography plays an important role in the screening and diagnosis of cardiovascular diseases. However, automated intelligent analysis of echocardiographic data remains challenging due to complex cardiac dynamics and strong view heterogeneity. In recent years, visual language models (VLM) have opened a new avenue for building ultrasound understanding systems for clinical decision support. Nevertheless, most existing methods formulate this task as a direct mapping from video and question to answer, making them vulnerable to template shortcuts and spurious explanations. To address these issues, we propose EchoTrust, an evidence-driven Actor-Verifier framework for trustworthy reasoning in echocardiography VLM-based agents. EchoTrust produces a structured intermediate representation that is subsequently analyzed by distinct roles, enabling more reliable and interpretable decision-making for high-stakes clinical applications.

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.

Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading to the development of diffusion multimodal large language models (dMLLMs). These models are expected to retain the reasoning capabilities of LLMs while enabling faster inference through parallel generation. However, when combined with Chain-of-Thought (CoT) reasoning, dMLLMs exhibit two critical issues. First, we observe that dMLLMs often generate the final answer token at a very early timestep. This trend indicates that the model determines the answer before sufficient reasoning, leading to degraded reasoning performance. Second, during the initial timesteps, dMLLMs show minimal dependency on visual prompts, exhibiting a fundamentally different pattern of visual information utilization compared to AR vision-language models. In summary, these findings indicate that dMLLMs tend to generate premature final answers without sufficiently grounding on visual inputs. To address these limitations, we propose Position and Step Penalty (PSP) and Visual Reasoning Guidance (VRG). PSP penalizes tokens in later positions during early timesteps, delaying premature answer generation and encouraging progressive reasoning across timesteps. VRG, inspired by classifier-free guidance, amplifies visual grounding signals to enhance the model's alignment with visual evidence. Extensive experiments across various dMLLMs demonstrate that our method achieves up to 7.5% higher accuracy while delivering more than 3x speedup compared to reasoning with four times more diffusion steps.

Vision-Language Models have achieved strong progress in ground-view visual understanding, yet they remain brittle in high-altitude Unmanned Aerial Vehicle scenes, where objects are tiny and densely packed, textures are repetitive, and top-down orientations are ambiguous. We introduce UAVReason, a large-scale UAV-native dataset and evaluation suite for studying unified aerial reasoning and generation under this nadir-view domain shift. UAVReason aligns RGB imagery, depth maps, semantic segmentation masks, captions, and question-answer pairs within a consistent aerial domain. It contains 23.6K captioned frames, 273K VQA pairs including 68.2K two-frame temporal questions, and 188.8K cross-modal generation samples across RGB, depth, and segmentation modalities. We further adapt UAVReason-Bagel as a unified understanding-and-generation baseline that jointly optimizes language reasoning and dense visual generation objectives. Experiments show that general-purpose VLMs and off-the-shelf unified generators struggle with UAV-native grounding, while UAVReason-Bagel substantially improves over its pretrained counterpart, increasing VQA-1F F1 from 0.394 to 0.711, VQA-2F F1 from 0.427 to 0.822, and heading-aware VQA F1 from 0.798 to 0.973. For generation, it improves segmentation mIoU to 0.143 and reduces KID from 0.078 to 0.048 for depth-segmentation-text-conditioned RGB synthesis. More importantly, our ablations reveal a bidirectional synergy between synthesis and reasoning. Dense generation objectives improve temporal semantic consistency, while language-level reasoning regularizes sparse-condition image synthesis. These results suggest that unified reasoning and generation provide effective geometry-aware structural priors for physically grounded aerial intelligence. All data, code, and evaluation tools will be released.

Accurate and timely identification of construction hazards around workers is essential for preventing workplace accidents. While large vision-language models (VLMs) demonstrate strong contextual reasoning capabilities, their high computational requirements limit their applicability in near real-time construction hazard detection. In contrast, small vision-language models (sVLMs) with fewer than 4 billion parameters offer improved efficiency but often suffer from reduced accuracy and hallucination when analyzing complex construction scenes. To address this trade-off, this study proposes a detection-guided sVLM framework that integrates object detection with multimodal reasoning for contextual hazard identification. The framework first employs a YOLOv11n detector to localize workers and construction machinery within the scene. The detected entities are then embedded into structured prompts to guide the reasoning process of sVLMs, enabling spatially grounded hazard assessment. Within this framework, six sVLMs (Gemma-3 4B, Qwen-3-VL 2B/4B, InternVL-3 1B/2B, and SmolVLM-2B) were evaluated in zero-shot settings on a curated dataset of construction site images with hazard annotations and explanatory rationales. The proposed approach consistently improved hazard detection performance across all models. The best-performing model, Gemma-3 4B, achieved an F1-score of 50.6%, compared to 34.5% in the baseline configuration. Explanation quality also improved significantly, with BERTScore F1 increasing from 0.61 to 0.82. Despite incorporating object detection, the framework introduces minimal overhead, adding only 2.5 ms per image during inference. These results demonstrate that integrating lightweight object detection with small VLM reasoning provides an effective and efficient solution for context-aware construction safety hazard detection.

When asked to describe a molecular diagram, a Vision-Language Model correctly identifies ``a benzene ring with an -OH group.'' When asked to reason about the same image, it answers incorrectly. The model can see but it cannot think about what it sees. We term this the perception-integration gap: a failure where visual information is successfully extracted but lost during downstream reasoning, invisible to single-configuration benchmarks that conflate perception with integration under one accuracy number. To systematically expose such failures, we introduce DISSECT, a 12,000-question diagnostic benchmark spanning Chemistry (7,000) and Biology (5,000). Every question is evaluated under five input modes -- Vision+Text, Text-Only, Vision-Only, Human Oracle, and a novel Model Oracle in which the VLM first verbalizes the image and then reasons from its own description -- yielding diagnostic gaps that decompose performance into language-prior exploitation, visual extraction, perception fidelity, and integration effectiveness. Evaluating 18~VLMs, we find that: (1) Chemistry exhibits substantially lower language-prior exploitability than Biology, confirming molecular visual content as a harder test of genuine visual reasoning; (2) Open-source models consistently score higher when reasoning from their own verbalized descriptions than from raw images, exposing a systematic integration bottleneck; and (3) Closed-source models show no such gap, indicating that bridging perception and integration is the frontier separating open-source from closed-source multimodal capability. The Model Oracle protocol is both model and benchmark agnostic, applicable post-hoc to any VLM evaluation to diagnose integration failures.

Most vision-language models (VLMs) apply a large language model (LLM) as the decoder, where the response tokens are generated sequentially through autoregression. Therefore, the number of output tokens can be the bottleneck of the end-to-end latency. However, different models may require vastly different numbers of output tokens to achieve comparable performance. In this work, we conduct a comprehensive analysis of the latency across different components of VLMs on simulated data. The experiment shows that a large model with fewer output tokens can be more efficient than a small model with a long output sequence. The empirical study on diverse real-world benchmarks confirms the observation that a large model can achieve better or comparable performance as a small model with significantly fewer output tokens. To leverage the efficiency of large models, we propose a multi-agent inference framework that keeps large models with short responses but transfers the key reasoning tokens from the small model when necessary. The comparison on benchmark tasks demonstrates that by reusing the reasoning tokens from small models, it can help approach the performance of a large model with its own reasoning, which confirms the effectiveness of our proposal.

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.

Recent advancements in Vision-Language Models (VLMs) have significantly pushed the boundaries of Visual Question Answering (VQA).However,high-resolution details can sometimes become noise that leads to hallucinations or reasoning errors. In this paper,we propose Degradation-Driven Prompting (DDP), a novel framework that improves VQA performance by strategically reducing image fidelity to force models to focus on essential structural information. We evaluate DDP across two distinct tasks. Physical attributes targets images prone to human misjudgment, where DDP employs a combination of 80p downsampling, structural visual aids (white background masks and orthometric lines), and In-Context Learning (ICL) to calibrate the model's focus. Perceptual phenomena addresses various machine-susceptible visual anomalies and illusions, including Visual Anomaly (VA), Color (CI), Motion(MI),Gestalt (GI), Geometric (GSI), and Visual Illusions (VI).For this task, DDP integrates a task-classification stage with specialized tools such as blur masks and contrast enhancement alongside downsampling. Our experimental results demonstrate that less is more: by intentionally degrading visual inputs and providing targeted structural prompts, DDP enables VLMs to bypass distracting textures and achieve superior reasoning accuracy on challenging visual benchmarks.

Traditional approaches to off-road autonomy rely on separate models for terrain classification, height estimation, and quantifying slip or slope conditions. Utilizing several models requires training each component separately, having task specific datasets, and fine-tuning. In this work, we present a zero-shot approach leveraging SAM2 for environment segmentation and a vision-language model (VLM) to reason about drivable areas. Our approach involves passing to the VLM both the original image and the segmented image annotated with numeric labels for each mask. The VLM is then prompted to identify which regions, represented by these numeric labels, are drivable. Combined with planning and control modules, this unified framework eliminates the need for explicit terrain-specific models and relies instead on the inherent reasoning capabilities of the VLM. Our approach surpasses state-of-the-art trainable models on high resolution segmentation datasets and enables full stack navigation in our Isaac Sim offroad environment.

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.

Human perception interprets video dynamics by constructing structured mental representations of entities, actions, and temporal boundaries before engaging in high-level reasoning. In contrast, current Video-LLMs typically rely on unstructured Chain-of-Thought (CoT), where crucial visual cues are obscured by verbose narration. While recent efforts ground reasoning in intermediate visual evidence, they rely on task-specific schemas that fail to generalize across diverse video understanding tasks. To address this, we introduce Structured Event Evidence, a unified, temporally ordered schema designed for general video reasoning. However, post-training a model to extract structured evidence while reasoning introduces a severe multi-objective optimization bottleneck, as candidate rollouts must simultaneously satisfy schema compliance, task accuracy, and reasoning budget. Standard reinforcement learning (RL) algorithms attempt to balance these objectives via static scalarization, enforcing a rigid accuracy-length trade-off across training and obscuring fine-grained reward signals. We resolve this by proposing Group-Relative Advantage Balancing (GRAB), which dynamically computes Pareto-optimal objective weights within each rollout group via a minimum-norm criterion over centered rewards. Operating strictly in reward space, GRAB incurs virtually zero computational overhead (<0.002% relative runtime to GRPO) and eliminates brittle weight tuning. Supported by our new PARSE-60K dataset (60K annotations across 35K videos) and a three-stage progressive curriculum, we train PARSE-4B. Across temporal grounding and video question-answering benchmarks, GRAB generates 13% to 39% fewer tokens while maintaining competitive accuracy with exhaustively hand-tuned static weights -- without requiring hyperparameter weight sweeps.

When video reasoning requires external knowledge, many systems with large multimodal models (LMMs) adopt retrieval augmentation to supply the missing context. Appending textual or multi-clip evidence, however, forces heterogeneous signals into a single attention space. We observe diluted attention and higher cognitive load even on non-long videos. The bottleneck is not only what to retrieve but how to represent and fuse external knowledge with the video backbone.We present Graph-to-Frame RAG (G2F-RAG), a training free and auditable paradigm that delivers knowledge in the visual space. On the offline stage, an agent builds a problem-agnostic video knowledge graph that integrates entities, events, spatial relations, and linked world knowledge. On the online stage, a hierarchical multi-agent controller decides whether external knowledge is needed, retrieves a minimal sufficient subgraph, and renders it as a single reasoning frame appended to the video. LMMs then perform joint reasoning in a unified visual domain. This design reduces cognitive load and leaves an explicit, inspectable evidence trail.G2F-RAG is plug-and-play across backbones and scales. It yields consistent gains on diverse public benchmarks, with larger improvements in knowledge-intensive settings. Ablations further confirm that knowledge representation and delivery matter. G2F-RAG reframes retrieval as visual space knowledge fusion for robust and interpretable video reasoning.

Reasoning VLMs can become more accurate while progressively losing visual grounding as they think. This creates task-conditional danger zones where low-entropy predictions are confident but ungrounded, a failure mode text-only monitoring cannot detect. Evaluating three reasoning VLMs on MathVista, HallusionBench, and MMMU_Pro, we find a pervasive evidence-collapse phenomenon: attention to annotated evidence regions drops substantially, often losing over half of evidence mass, as reasoning unfolds. Full-response entropy is the most reliable text-only uncertainty signal under cross-dataset transfer, yet adding vision features with a single global linear rule is brittle and often degrades transfer. An entropy-vision interaction model reveals a task-conditional regime: lowentropy, visually disengaged predictions are hazardous on sustained visual-reference tasks but benign on symbolic tasks. Using this structure, a targeted vision veto reduces selective risk by up to 1.9 percentage points at 90% coverage, while avoiding degradations where disengagement is expected. The results support task-aware multimodal monitoring for safe deployment under distribution shift.

Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments. Recent advances in Vision Language Models (VLMs) and Vision Language Action (VLA) models introduce common-sense reasoning through large-scale multimodal pretraining, enabling zero-shot performance across tasks. However, these models still lack explicit mechanisms to represent and update belief, limiting their ability to reason like humans or capture the evolving human intent over long-horizon. To address this, we propose a belief-aware VLM framework that integrates retrieval-based memory and reinforcement learning. Instead of learning an explicit belief model, we approximate belief using a vector-based memory that retrieves relevant multimodal context, which is incorporated into the VLM for reasoning. We further refine decision-making using a reinforcement learning policy over the VLM latent space. We evaluate our approach on publicly available VQA datasets such as HD-EPIC and demonstrate consistent improvements over zero-shot baselines, highlighting the importance of belief-aware reasoning.

Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance remains limited for complex tables with hierarchical layouts. In this paper, we identify a critical Perception Bottleneck through quantitative analysis. We find that as task complexity scales, the number of involved discrete visual regions increases disproportionately. This processing density leads to an internal "Perceptual Overload," where MLLMs struggle to maintain accurate spatial attention during implicit generation. To address this bottleneck, we introduce TableVision, a large-scale, trajectory-aware benchmark designed for spatially grounded reasoning. TableVision stratifies tabular tasks into three cognitive levels (Perception, Reasoning, and Analysis) across 13 sub-categories. By utilizing a rendering-based deterministic grounding pipeline, the dataset explicitly couples multi-step logical deductions with pixel-perfect spatial ground truths, comprising 6,799 high-fidelity reasoning trajectories. Our empirical results, supported by diagnostic probing, demonstrate that explicit spatial constraints significantly recover the reasoning potential of MLLMs. Furthermore, our two-stage decoupled framework achieves a robust 12.3% overall accuracy improvement on the test set. TableVision provides a rigorous testbed and a fresh perspective on the synergy between perception and logic in document understanding.

In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for stable and effective learning. However, existing self-evolution methods predominantly rely on majority voting to select the most frequent output as the pseudo-golden answer, which may stem from the model's intrinsic biases rather than guaranteeing the objective correctness of the reasoning paths. To counteract the degradation, we propose Continuous Softened Retracing reSampling (CSRS) in MLLM self-evolution. Specifically, we introduce a Retracing Re-inference Mechanism (RRM) that the model re-inferences from anchor points to expand the exploration of long-tail reasoning paths. Simultaneously, we propose Softened Frequency Reward (SFR), which replaces binary rewards with continuous signals, calibrating reward based on the answers' frequency across sampled reasoning sets. Furthermore, incorporated with Visual Semantic Perturbation (VSP), CSRS ensures the model prioritizes mathematical logic over visual superficiality. Experimental results demonstrate that CSRS significantly enhances the reasoning performance of Qwen2.5-VL-7B on benchmarks such as MathVision. We achieve state-of-the-art (SOTA) results in unsupervised self-evolution on geometric tasks. Our code is avaible at https://github.com/yyy195/CSRS.

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.

Understanding long videos requires extracting query-relevant information from long sequences under tight compute budgets. Existing text-then-LLM pipelines lose fine-grained visual cues, while video-based multimodal large language models (MLLMs) can keep visual details but are too frame-hungry and computationally expensive. In this work, we aim to harness MLLMs for efficient video understanding. We propose ProVCA, a progressive video condensation agent that iteratively locates key video frames at multiple granularities. ProVCA first adopts a segment localization module to identify the video segment relevant to the query, then a snippet selection module to select important snippets based on similarity, and finally a keyframe refinement module to pinpoint specific keyframes in those snippets. By progressively narrowing the scope from coarse segments to fine frames, ProVCA identifies a small set of keyframes for MLLM-based reasoning. ProVCA achieves state-of-the-art zero-shot accuracies of 69.3% on EgoSchema, 80.5% on NExT-QA, and 77.7% on IntentQA, while using fewer frames than previous training-free methods.

Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual reasoning, they remain fragile to viewpoint changes, as pixel-wise warping is highly sensitive to small depth errors and often introduces geometric distortions. Drawing on theories of mental imagery that posit part-level structural representations as the basis for human perspective transformation, we examine whether image tokens in ViT-based MLLMs serve as an effective substrate for viewpoint changes. We compare forward and backward warping, finding that backward token warping, which defines a dense grid on the target view and retrieves a corresponding source-view token for each grid point, achieves greater stability and better preserves semantic coherence under viewpoint shifts. Experiments on our proposed ViewBench benchmark demonstrate that token-level warping enables MLLMs to reason reliably from nearby viewpoints, consistently outperforming all baselines including pixel-wise warping approaches, spatially fine-tuned MLLMs, and a generative warping method.

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present in their internal representations. Prior work has attributed this ``hidden-in-plain-sight'' gap to the language model, but the cause remains unexplained. In this work, we demonstrate that this gap arises from the language model's lack of semantic labels for fine-grained visual details: when visual entities can be mapped to known concepts, VLMs bypass visual comparison and reason through language; when they cannot, VLMs resort to brittle and hallucinated descriptions. We verify this across semantic correspondence, synthetic shape matching, and face matching, and find that VLMs perform much better when the relevant entities are nameable than when they are unnamable. Mechanistically, Logit Lens analysis confirms that VLMs explicitly recover semantic labels for nameable entities and surface more unique tokens compared to unnameable entities. Furthermore, we show that this limitation can be addressed: teaching completely arbitrary names for unknown entities improves performance. More importantly, task-specific finetuning yields even stronger generalization without relying on language priors, i.e., through real visual perception. Our findings suggest that current VLM failures on visual tasks reflect a learned shortcut rather than a fundamental limitation of multimodal reasoning. Code and datasets are available at https://github.com/Patchwork53/VLMs-Need-Words-COLM2026.

This work investigates the fundamental fragility of state-of-the-art Vision-Language Models (VLMs) under basic geometric transformations. While modern VLMs excel at semantic tasks such as recognizing objects in canonical orientations and describing complex scenes, they exhibit systematic failures at a more fundamental level: lack of robust spatial invariance and equivariance required to reliably determine object identity under simple rotations, scaling, and identity transformations. We demonstrate this limitation through a systematic evaluation across diverse visual domains, including symbolic sketches, natural photographs, and abstract art. Performance drops sharply as semantic content becomes sparse, and this behavior is observed across architectures, model capacities, and prompting strategies. Overall, our results reveal a systematic gap between semantic understanding and spatial reasoning in current VLMs, highlighting the need for stronger geometric grounding in future multimodal systems.

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.

Large Vision-Language Models (LVLMs) have achieved remarkable proficiency in explicit visual recognition, effectively describing what is directly visible in an image. However, a critical cognitive gap emerges when the visual input serves only as a clue rather than the answer. We identify that current models struggle with the complex, multi-step reasoning required to solve problems where information is not explicitly depicted. Successfully solving a rebus puzzle requires a distinct cognitive workflow: the model must extract visual and textual attributes, retrieve linguistic prior knowledge (such as idioms), and perform abstract mapping to synthesize these elements into a meaning that exists outside the pixel space. To evaluate this neurosymbolic capability, we introduce RebusBench, a benchmark of 1,164 puzzles designed to test this specific integration of perception and knowledge. Our evaluation of state-of-the-art models (including Qwen, InternVL, and LLaVA) shows a severe deficiency: performance saturates below 10% Exact Match and 20% semantic accuracy, with no significant improvement observed from model scaling or In-Context Learning (ICL). These findings suggest that while models possess the necessary visual and linguistic components, they lack the cognitive reasoning glue to connect them. Project page available at https://amirkasaei.com/rebusbench/.