{"total":29,"rows":[{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"area":"lr"},{"id":"2512.05965","title":"EditThinker: Unlocking Iterative Reasoning for Any Image Editor","created":"2025-12-05","cited_by_count":25,"area":"lr"},{"id":"2510.12697","title":"Multi-Agent Debate for LLM Judges with Adaptive Stability Detection","created":"2025-10-14","cited_by_count":23,"area":"lr"},{"id":"2503.20271","title":"ViLBench: A Suite for Vision-Language Process Reward Modeling","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2507.11662","title":"Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification","created":"2025-07-15","cited_by_count":14,"area":"lr"},{"id":"2511.22134","title":"DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action","created":"2025-11-27","cited_by_count":12,"area":"lr"},{"id":"2503.01891","title":"MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problems","created":"2025-02-27","cited_by_count":10,"area":"lr"},{"id":"2511.20022","title":"WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2505.13403","title":"MR. Judge: Multimodal Reasoner as a Judge","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2505.18601","title":"Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"id":"2505.23449","title":"CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection","created":"2025-05-29","cited_by_count":6,"area":"lr"},{"id":"2506.23009","title":"MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models","created":"2025-06-28","cited_by_count":4,"area":"lr"},{"id":"2602.06663","title":"PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks","created":"2026-02-06","cited_by_count":4,"area":"lr"},{"id":"2502.11300","title":"CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?","created":"2025-02-16","cited_by_count":3,"area":"lr"},{"id":"2506.00806","title":"Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2603.21526","title":"VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2606.02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2508.08275","title":"MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis","created":"2025-07-31","cited_by_count":2,"area":"lr"},{"id":"2508.11350","title":"HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language Model","created":"2025-08-15","cited_by_count":2,"area":"lr"},{"id":"2604.22868","title":"Probing Visual Planning in Image Editing Models","created":"2026-04-23","cited_by_count":2,"area":"lr"},{"id":"2508.04576","title":"ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judges","created":"2025-08-06","cited_by_count":1,"area":"lr"},{"id":"2510.19001","title":"Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts","created":"2025-10-21","cited_by_count":1,"area":"lr"},{"id":"2605.19995","title":"CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2608.18111","title":"Solving Is Not Drawing: A Benchmark for Diagrammatic Reasoning in Olympiad Geometry","created":"2026-06-23","cited_by_count":0,"area":"lr"},{"id":"2608.21022","title":"Recognition-Conditioned Reasoning: A Training-Free Multimodal-LLM Pipeline for Fine-Grained Micro-Action Understanding","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2608.30751","title":"Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models","created":"2026-08-31","cited_by_count":0,"area":"lr"}],"next_cursor":null}