{"total":52,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"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":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.17472","title":"T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation","created":"2025-08-24","cited_by_count":38,"area":"lr"},{"id":"2509.09680","title":"FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark","created":"2025-09-11","cited_by_count":38,"area":"lr"},{"id":"2510.14958","title":"MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning","created":"2025-10-16","cited_by_count":35,"area":"lr"},{"id":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2511.23002","title":"JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization","created":"2025-11-28","cited_by_count":31,"area":"alignment"},{"id":"2601.18543","title":"GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning","created":"2026-01-26","cited_by_count":24,"area":"lr"},{"id":"2602.13823","title":"Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings","created":"2026-02-14","cited_by_count":24,"area":"lr"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2510.11718","title":"CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images","created":"2025-10-13","cited_by_count":23,"area":"lr"},{"id":"2510.12784","title":"SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models","created":"2025-10-14","cited_by_count":22,"area":"synth"},{"id":"2511.15065","title":"Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks","created":"2025-11-19","cited_by_count":22,"area":"lr"},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"area":"mllm"},{"id":"2603.16870","title":"Demystifying Video Reasoning","created":"2026-03-17","cited_by_count":14,"area":"lr"},{"id":"2510.10518","title":"VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning","created":"2025-10-12","cited_by_count":12,"area":"lr"},{"id":"2507.16663","title":"Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs","created":"2025-07-22","cited_by_count":10,"area":"synth"},{"id":"2510.06871","title":"SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2508.11433","title":"MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation","created":"2025-08-15","cited_by_count":9,"area":"lr"},{"id":"2512.01236","title":"PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards","created":"2025-12-01","cited_by_count":9,"area":null},{"id":"2601.03468","title":"Understanding Reward Hacking in Text-to-Image Reinforcement Learning","created":"2026-01-06","cited_by_count":9,"area":"alignment"},{"id":"2509.22761","title":"MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2510.08157","title":"Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing","created":"2025-10-09","cited_by_count":6,"area":"lr"},{"id":"2603.06043","title":"Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models","created":"2026-03-06","cited_by_count":6,"area":null},{"id":"2508.18032","title":"Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation","created":"2025-08-25","cited_by_count":5,"area":"lr"},{"id":"2602.15772","title":"Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2510.18263","title":"From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation","created":"2025-10-21","cited_by_count":4,"area":"deeprl"},{"id":"2603.27866","title":"Wan-R1: Verifiable-Reinforcement Learning for Video Reasoning","created":"2026-03-29","cited_by_count":4,"area":"lr"},{"id":"2605.12374","title":"Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models","created":"2026-05-12","cited_by_count":4,"area":"lr"},{"id":"2601.04589","title":"MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2603.01893","title":"Generative Visual Chain-of-Thought for Image Editing","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2604.13491","title":"FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2604.24625","title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","created":"2026-04-27","cited_by_count":3,"area":"lr"},{"id":"2506.13363","title":"Efficient Medical VIE via Reinforcement Learning","created":"2025-06-16","cited_by_count":2,"area":"deeprl"},{"id":"2511.11780","title":"Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing","created":"2025-11-15","cited_by_count":2,"area":"deeprl"},{"id":"2604.04500","title":"Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward","created":"2026-04-06","cited_by_count":2,"area":"lr"},{"id":"2606.24849","title":"IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation","created":"2026-06-23","cited_by_count":2,"area":"lr"},{"id":"2506.02015","title":"OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generation","created":"2025-05-28","cited_by_count":1,"area":"mllm"},{"id":"2603.27959","title":"MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.23500","title":"B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2602.02004","title":"ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2603.02712","title":"From \"What\" to \"How\": Constrained Reasoning for Autoregressive Image Generation","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2605.16848","title":"Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction","created":"2026-05-16","cited_by_count":0,"area":"wm"},{"id":"2606.04264","title":"UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2606.20970","title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.20336","title":"WithEveryone: Unified Planning and Identity Grounding for Group Image Generation","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20882","title":"LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.21713","title":"The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.14615","title":"Open-UniMo: Towards Unified Motion-Language Understanding and Generation in the Open World","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.40305","title":"Looped Diffusion Transformer","created":"2026-09-30","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}