{"total":23,"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":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2510.15110","title":"DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning","created":"2025-10-16","cited_by_count":35,"area":"lr"},{"id":"2601.14750","title":"Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning","created":"2026-01-21","cited_by_count":20,"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":"2509.07339","title":"Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity","created":"2025-09-09","cited_by_count":9,"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":"2601.08310","title":"ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning","created":"2026-01-13","cited_by_count":7,"area":"lr"},{"id":"2511.00640","title":"DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2509.26226","title":"Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners","created":"2025-09-30","cited_by_count":5,"area":"lr"},{"id":"2510.06052","title":"MixReasoning: Switching Modes to Think","created":"2025-10-07","cited_by_count":3,"area":"lr"},{"id":"2511.14258","title":"Entropy-Guided Reasoning Compression","created":"2025-11-18","cited_by_count":3,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2606.22305","title":"Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning","created":"2026-06-21","cited_by_count":2,"area":"lr"},{"id":"2601.02825","title":"SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2602.01198","title":"A State-Transition Framework for Efficient LLM Reasoning","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2605.08665","title":"Hint Tuning: Less Data Makes Better Reasoners","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2607.07976","title":"When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2510.25065","title":"Rewarding Structural Conformance of Reasoning using Process Mining","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2512.19728","title":"Hard Negative Sample-Augmented DPO Post-Training for Small Language Models","created":"2025-12-17","cited_by_count":0,"area":"lr"},{"id":"2604.04120","title":"Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression","created":"2026-04-05","cited_by_count":0,"area":"lr"},{"id":"2604.05643","title":"Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2605.11625","title":"Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning","created":"2026-05-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}