{"total":33,"rows":[{"id":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289,"area":"lr"},{"id":"2508.20751","title":"Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning","created":"2025-08-28","cited_by_count":92,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2505.14268","title":"Think-J: Learning to Think for Generative LLM-as-a-Judge","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2510.11369","title":"Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment","created":"2025-10-13","cited_by_count":18,"area":"lr"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2505.20640","title":"IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios","created":"2025-05-27","cited_by_count":13,"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":"2508.03556","title":"VRPRM: Process Reward Modeling via Visual Reasoning","created":"2025-08-05","cited_by_count":11,"area":"lr"},{"id":"2505.24499","title":"Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning","created":"2025-05-30","cited_by_count":8,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2510.01010","title":"ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning","created":"2025-10-01","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2603.06652","title":"PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment","created":"2026-02-28","cited_by_count":5,"area":"lr"},{"id":"2512.08980","title":"Training Multi-Image Vision Agents via End2End Reinforcement Learning","created":"2025-12-05","cited_by_count":4,"area":"lr"},{"id":"2603.06665","title":"Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2604.24583","title":"Improving Vision-language Models with Perception-centric Process Reward Models","created":"2026-04-27","cited_by_count":4,"area":"lr"},{"id":"2505.17897","title":"T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation","created":"2025-05-23","cited_by_count":3,"area":"lr"},{"id":"2512.23169","title":"REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2602.07533","title":"Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models","created":"2026-02-07","cited_by_count":3,"area":"lr"},{"id":"2603.04002","title":"Discriminative Perception via Anchored Description for Reasoning Segmentation","created":"2026-03-04","cited_by_count":3,"area":"lr"},{"id":"2603.12648","title":"From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space","created":"2026-03-13","cited_by_count":3,"area":"lr"},{"id":"2602.00085","title":"CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":"lr"},{"id":"2605.05922","title":"Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2505.23265","title":"SPR-128K: A New Benchmark for Spatial Plausibility Reasoning with Multimodal Large Language Models","created":"2025-05-29","cited_by_count":1,"area":"lr"},{"id":"2511.10055","title":"Physical Plausibility Reasoning via HCM-GRPO: Empowering Compact Model for Superior Performance","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2603.19779","title":"One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment","created":"2026-03-20","cited_by_count":1,"area":"lr"},{"id":"2605.07872","title":"Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2608.10908","title":"Order Matters: LVLMs as Judges for Temporal Reasoning in Image Sequences","created":"2026-08-11","cited_by_count":1,"area":"lr"},{"id":"2511.05393","title":"PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment","created":"2025-11-07","cited_by_count":0,"area":"lr"},{"id":"2604.16858","title":"Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement","created":"2026-04-18","cited_by_count":0,"area":"lr"},{"id":"2610.20089","title":"When Pairwise Preferences Cycle: A Reliability-Anchored Preference Walk for Video GRPO","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}