arXiv:2511. 17731v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs).
The paper introduces Auto-Comp, a fully automated, concept-driven pipeline that generates photorealistic compositional benchmarks for vision‑language models. Auto‑Comp creates paired Minimal and Contextual samples for each concept, enabling isolation of core binding abilities from visio‑linguistic complexity. Evaluations across 25 models reveal consistent failures in attribute and relational binding, with context helping relational tasks but hindering attribute tasks due to visual clutter.
arXiv:2510.09302v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in difficult purely textual mathematical reasoning tasks, eve...
arXiv:2507. 16518v3 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities.
arXiv:2605. 18160v2 Announce Type: replace-cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information.
UReason is a benchmark that evaluates how well unified multimodal models (UMMs) align textual reasoning with image generation. It contains 2,000 human‑curated instances across five reasoning‑intensive tasks—Code, Arithmetic, Spatial, Attribute, and Text—and compares direct generation, reasoning‑guided generation, and decontextualized generation. The study finds that while reasoning‑guided generation improves over direct generation, decontextualized generation consistently outperforms it, indicating that the visual semantics in textual reasoning are not reliably reflected in the generated images.
CoVA‑SFT is a new large‑scale dataset comprising 51.9K samples and over 222K multimodal reasoning steps that teach models to interleave text and visual abstractions across five layout families and 17 complex tasks. It includes explicit rationale formulations, agentic renderings, and verification loops to help models build and maintain internal visual workspaces for purely textual reasoning problems. A companion benchmark, CoVA‑Bench, contains 1,700 held‑out test samples for reproducible evaluation, and models fine‑tuned on CoVA‑SFT outperform all interleaved CoT baselines by more than 2× on average, though they still lag behind strong text‑only CoT baselines.
arXiv:2509. 05208v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored.
GeoReform is a reflective formalization evolution framework designed to improve multimodal geometry problem solving by treating formalization as an optimizable policy rather than a fixed parser. It iteratively runs the reasoning pipeline, collects failures, diagnoses representation defects, and mutates the policy to better select, ground, group, and present geometric entities, relations, constraints, and targets. On the Geometry3K benchmark, GeoReform raises Qwen3VL-2B accuracy from 42.0% to 56.0%, demonstrating that effective formalization is crucial for enhancing multimodal geometry reasoning.
GraphVerse is a new benchmark for multimodal large language models that tests visual graph reasoning by combining perception, graph-based visual inputs, and multi-step reasoning. It introduces Graph-centric Image Editing strategies to actively challenge models while preserving semantics, and offers a VGR-Score metric that evaluates reasoning quality beyond simple answer accuracy. Experiments show current models have limitations in VGR and demonstrate the effectiveness of GraphVerse for broader multimodal reasoning tasks.
The paper surveys Multimodal Code Intelligence, focusing on tasks where code is generated, edited, refined, or reasoned about under visually grounded inputs such as screenshots, charts, and videos. It categorizes the field by the role of code—rendered artifact, editable structure, intermediate reasoning trace, or executable tool interface—and organizes benchmarks into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. The authors argue that reliable evaluation must include evidence of semantics and interaction beyond visual fidelity, and propose four verification-centered research directions to advance the field toward evidence-grounded executable systems.
Vision2Code is a new benchmark for image-to-code generation that covers 15 domains and 539 test examples without relying on reference source code. It evaluates generated programs by executing them and comparing rendered outputs to the original images using domain‑specific rubrics, yielding scores that correlate better with human judgments than generic metrics. The study shows domain variability in model performance and demonstrates that the scoring method can improve fine‑tuning of models like Qwen3.5‑9B and Phi‑4‑MM via rejection sampling.