{"total":17,"rows":[{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2510.08457","title":"ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping","created":"2025-10-09","cited_by_count":17,"area":"lr"},{"id":"2601.21919","title":"Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":13,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2506.04574","title":"Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis","created":"2025-06-05","cited_by_count":6,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2509.25827","title":"Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2509.17743","title":"VideoPro: Adaptive Program Reasoning for Long Video Understanding","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2602.03485","title":"Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning","created":"2026-02-03","cited_by_count":3,"area":"lr"},{"id":"2511.02280","title":"SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2511.13242","title":"MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection","created":"2025-11-17","cited_by_count":0,"area":"lr"},{"id":"2602.11748","title":"Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2602.12287","title":"Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction","created":"2026-01-21","cited_by_count":0,"area":"lr"},{"id":"2605.28398","title":"HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.07108","title":"DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling","created":"2026-06-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}