{"total":14,"rows":[{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2510.12712","title":"Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning","created":"2025-10-14","cited_by_count":29,"area":"lr"},{"id":"2510.01681","title":"Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning","created":"2025-10-02","cited_by_count":9,"area":"lr"},{"id":"2506.02537","title":"VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning","created":"2025-06-03","cited_by_count":7,"area":"lr"},{"id":"2510.09302","title":"CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2601.16520","title":"TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning","created":"2026-01-23","cited_by_count":4,"area":"lr"},{"id":"2508.06009","title":"MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models","created":"2025-08-08","cited_by_count":3,"area":"lr"},{"id":"2510.08987","title":"Towards Efficient Multimodal Unified Reasoning Model via Model Merging","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2603.22689","title":"Think 360{\\deg}: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth","created":"2026-03-24","cited_by_count":0,"area":"lr"},{"id":"2605.22413","title":"From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.26041","title":"How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"id":"2608.17895","title":"BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2608.26141","title":"AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2608.30678","title":"OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding","created":"2026-08-31","cited_by_count":0,"area":"lr"}],"next_cursor":null}