CiteVQA requires models to cite specific document regions with bounding boxes alongside answers and finds that even the strongest MLLMs frequently cite the wrong region, with top SAA scores of only 76.0 for closed models and 22.5 for open-source ones.
hub Mixed citations
Thyme: Think Beyond Images
Mixed citation behavior. Most common role is background (50%).
32
Pith papers citing it
Background
50% of classified citations
abstract
Following OpenAI's introduction of the ``thinking with images'' concept, recent efforts have explored stimulating the use of visual information in the reasoning process to enhance model performance in perception and reasoning tasks. However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing Thyme (Think Beyond Images), a novel paradigm for enabling MLLMs to transcend existing ``think with images'' approaches by autonomously generating and executing diverse image processing and computational operations via executable code. This approach not only facilitates a rich, on-the-fly set of image manipulations (e.g., cropping, rotation, contrast enhancement) but also allows for mathematical computations, all while maintaining high autonomy in deciding when and how to apply these operations. We activate this capability through a two-stage training strategy: an initial SFT on a curated dataset of 500K samples to teach code generation, followed by a RL phase to refine decision-making. For the RL stage, we manually collect and design high-resolution question-answer pairs to increase the learning difficulty, and we propose GRPO-ATS (Group Relative Policy Optimization with Adaptive Temperature Sampling), an algorithm that applies distinct temperatures to text and code generation to balance reasoning exploration with code execution precision. We conduct extensive experimental analysis and ablation studies. Comprehensive evaluations on nearly 20 benchmarks show that Thyme yields significant and consistent performance gains, particularly in challenging high-resolution perception and complex reasoning tasks.
hub tools
citation-role summary
background 8
dataset 4
baseline 2
citation-polarity summary
representative citing papers
S1-VL combines structured scientific reasoning with iterative image manipulation via code execution to reach state-of-the-art results on visual and scientific reasoning benchmarks.
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
A decoupled question-conditioned image editor trained via supervised imitation then VLM-reward enhancement improves MLLM visual reasoning Pass@1 by 4.6-5.5 points across models and tasks.
V-ABS is an action-observer beam search method with entropy-based adaptive weighting and an 80k-sample SFT dataset that delivers 19.7% average gains on visual reasoning tasks for MLLMs.
Perceval is a perception-centric PRM that detects token-level perceptual errors in VLMs, supporting token-advantage RL training and iterative test-time scaling for improved reasoning.
HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks.
E3VS-Bench supplies 99 3D Gaussian Splatting scenes and 2,014 episodes to test whether embodied agents can use unrestricted 5-DoF viewpoint control to answer questions that depend on fine-grained visual details visible only from specific angles.
V-Reflection introduces a think-then-look mechanism where MLLM latent states actively interrogate visual features via two-stage distillation from a box-guided teacher to a dynamic autoregressive student, narrowing the fine-grained perception gap on benchmarks.
SynthFun3D generates synthetic 3D functionality segmentation data from action descriptions via object retrieval and scene arrangement, yielding consistent gains of +2.2 mAP, +6.3 mAR, and +5.7 mIoU when augmenting real data for VLM training.
Maestro uses outcome-based RL to train a lightweight policy that orchestrates ensembles of frozen expert models and skills, reporting 70.1% average accuracy across ten multimodal benchmarks and outperforming GPT-5 and Gemini-2.5-Pro while generalizing to unseen components.
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
SCOLAR fixes information gain collapse in latent visual reasoning by generating independent auxiliary visual tokens via a detransformer, extending acceptable CoT length over 30x and delivering +14.12% gains on reasoning benchmarks.
SIEVES improves selective prediction coverage by up to 3x on OOD VQA benchmarks by training a selector to score the quality of visual evidence produced by reasoner models, generalizing across benchmarks and proprietary models without internal access or per-task retraining.
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
Perception Programs rewrite dense visual tool outputs into language-native summaries, boosting MLLM accuracy by 15-45% absolute on BLINK perception tasks and setting new state-of-the-art results.
Q-Zoom achieves up to 4.39x inference speedup in high-resolution MLLM scenarios via query-aware gating and region localization, matching or exceeding baseline accuracy on document and high-res benchmarks.
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
CharTool equips MLLMs with cropping and code tools plus agentic RL on DuoChart data to raise chart-reasoning accuracy by up to 9.78 percent on benchmarks.
MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.
AdaTooler-V trains MLLMs to adaptively use vision tools via AT-GRPO reinforcement learning and new datasets, reaching 89.8% on V* and outperforming GPT-4o.
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
DeepEyesV2 uses a two-stage cold-start plus reinforcement learning pipeline to produce an agentic multimodal model that adaptively invokes tools and outperforms direct RL on real-world reasoning benchmarks.
citing papers explorer
-
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
CiteVQA requires models to cite specific document regions with bounding boxes alongside answers and finds that even the strongest MLLMs frequently cite the wrong region, with top SAA scores of only 76.0 for closed models and 22.5 for open-source ones.
-
S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images
S1-VL combines structured scientific reasoning with iterative image manipulation via code execution to reach state-of-the-art results on visual and scientific reasoning benchmarks.
-
EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
-
ETCHR: Editing To Clarify and Harness Reasoning
A decoupled question-conditioned image editor trained via supervised imitation then VLM-reward enhancement improves MLLM visual reasoning Pass@1 by 4.6-5.5 points across models and tasks.
-
V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning
V-ABS is an action-observer beam search method with entropy-based adaptive weighting and an 80k-sample SFT dataset that delivers 19.7% average gains on visual reasoning tasks for MLLMs.
-
Improving Vision-language Models with Perception-centric Process Reward Models
Perceval is a perception-centric PRM that detects token-level perceptual errors in VLMs, supporting token-advantage RL training and iterative test-time scaling for improved reasoning.
-
Hybrid Latent Reasoning with Decoupled Policy Optimization
HyLaR with DePO enables effective RL in hybrid discrete-continuous spaces for multimodal models, outperforming prior MLLMs on perception and understanding benchmarks.
-
E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
E3VS-Bench supplies 99 3D Gaussian Splatting scenes and 2,014 episodes to test whether embodied agents can use unrestricted 5-DoF viewpoint control to answer questions that depend on fine-grained visual details visible only from specific angles.
-
V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators
V-Reflection introduces a think-then-look mechanism where MLLM latent states actively interrogate visual features via two-stage distillation from a box-guided teacher to a dynamic autoregressive student, narrowing the fine-grained perception gap on benchmarks.
-
Action-guided generation of 3D functionality segmentation data
SynthFun3D generates synthetic 3D functionality segmentation data from action descriptions via object retrieval and scene arrangement, yielding consistent gains of +2.2 mAP, +6.3 mAR, and +5.7 mIoU when augmenting real data for VLM training.
-
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
Maestro uses outcome-based RL to train a lightweight policy that orchestrates ensembles of frozen expert models and skills, reporting 70.1% average accuracy across ten multimodal benchmarks and outperforming GPT-5 and Gemini-2.5-Pro while generalizing to unseen components.
-
Leveraging Latent Visual Reasoning in Silence
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
-
Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model
SCOLAR fixes information gain collapse in latent visual reasoning by generating independent auxiliary visual tokens via a detransformer, extending acceptable CoT length over 30x and delivering +14.12% gains on reasoning benchmarks.
-
SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
SIEVES improves selective prediction coverage by up to 3x on OOD VQA benchmarks by training a selector to score the quality of visual evidence produced by reasoner models, generalizing across benchmarks and proprietary models without internal access or per-task retraining.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
Perception Programs rewrite dense visual tool outputs into language-native summaries, boosting MLLM accuracy by 15-45% absolute on BLINK perception tasks and setting new state-of-the-art results.
-
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
Q-Zoom achieves up to 4.39x inference speedup in high-resolution MLLM scenarios via query-aware gating and region localization, matching or exceeding baseline accuracy on document and high-res benchmarks.
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
-
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
CharTool equips MLLMs with cropping and code tools plus agentic RL on DuoChart data to raise chart-reasoning accuracy by up to 9.78 percent on benchmarks.
-
MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?
MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.
-
AdaTooler-V: Adaptive Tool-Use for Images and Videos
AdaTooler-V trains MLLMs to adaptively use vision tools via AT-GRPO reinforcement learning and new datasets, reaching 89.8% on V* and outperforming GPT-4o.
-
Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
-
DeepEyesV2: Toward Agentic Multimodal Model
DeepEyesV2 uses a two-stage cold-start plus reinforcement learning pipeline to produce an agentic multimodal model that adaptively invokes tools and outperforms direct RL on real-world reasoning benchmarks.
-
CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
Presents CaptchaBench benchmark and CaptchaMind RL solver achieving 82.9% success on benchmark tasks and 71% on real-world CAPTCHAs via explicit reasoning process supervision.
-
Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth
Constraining visual token budget per observation during VLM training forces genuine active perception and delivers 5% average relative improvement without auxiliary losses or architecture changes.
-
Perceptual Flow Network for Visually Grounded Reasoning
PFlowNet decouples perception from reasoning, integrates multi-dimensional rewards with vicinal geometric shaping via variational RL, and reports new SOTA results on V* Bench (90.6%) and MME-RealWorld-lite (67.0%).
-
Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images
TTSP resolves the Grounding Paradox by treating perception as a scalable test-time process that generates, filters, and iteratively refines multiple visual exploration traces, outperforming baselines on high-resolution and multimodal reasoning tasks.
-
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.
- Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
- VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning