{"total":36,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2509.21320","title":"SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines","created":"2025-09-25","cited_by_count":11,"area":"lr"},{"id":"2512.01274","title":"SUPERChem: A Multimodal Reasoning Benchmark in Chemistry","created":"2025-12-01","cited_by_count":9,"area":"lr"},{"id":"2510.10182","title":"A Survey of Inductive Reasoning for Large Language Models","created":"2025-10-11","cited_by_count":8,"area":"lr"},{"id":"2602.09443","title":"P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2509.24285","title":"SCI-Verifier: Scientific Verifier with Thinking","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2512.14989","title":"Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams","created":"2025-12-17","cited_by_count":6,"area":"lr"},{"id":"2604.02710","title":"V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views","created":"2026-04-03","cited_by_count":6,"area":"lr"},{"id":"2510.13166","title":"CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2512.16978","title":"A Benchmark for Omni-Modal Reasoning in Long Videos","created":"2025-12-18","cited_by_count":5,"area":"lr"},{"id":"2604.21409","title":"S1-VL: Scientific Multimodal Reasoning Model with Thinking-with-Images","created":"2026-04-23","cited_by_count":5,"area":"lr"},{"id":"2510.08540","title":"MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2512.10739","title":"Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving","created":"2025-12-11","cited_by_count":4,"area":"lr"},{"id":"2510.15600","title":"Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward Mechanism","created":"2025-10-17","cited_by_count":3,"area":"lr"},{"id":"2511.12485","title":"ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction","created":"2025-11-16","cited_by_count":3,"area":"lr"},{"id":"2604.03318","title":"EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2606.02835","title":"Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2512.06835","title":"Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning","created":"2025-12-07","cited_by_count":2,"area":"lr"},{"id":"2606.04579","title":"SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2511.07070","title":"RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services","created":"2025-11-10","cited_by_count":1,"area":"lr"},{"id":"2511.21397","title":"Understanding the Effects of Distractors on Reasoning Vision-Language Models","created":"2025-11-26","cited_by_count":1,"area":"lr"},{"id":"2601.16480","title":"TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2603.19254","title":"FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.28361","title":"Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2605.11636","title":"Seir\\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2606.03503","title":"ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2607.20868","title":"ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?","created":"2026-07-23","cited_by_count":1,"area":"lr"},{"id":"2608.23982","title":"Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning","created":"2026-08-25","cited_by_count":1,"area":"lr"},{"id":"2602.11731","title":"Thinking with Drafting: Optical Decompression via Logical Reconstruction","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2603.10335","title":"Fuel Gauge: Estimating Chain-of-Thought Length Ahead of Time in Large Multimodal Models","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2605.18799","title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.28077","title":"MACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram Parsing","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.07689","title":"Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2609.18991","title":"Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry Reasoning","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2609.35336","title":"TMCS: Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}