{"total":34,"rows":[{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62,"area":"lr"},{"id":"2506.08989","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":42,"area":"lr"},{"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":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2508.10293","title":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","created":"2025-08-14","cited_by_count":28,"area":"lr"},{"id":"2508.15827","title":"Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models","created":"2025-08-18","cited_by_count":21,"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":"2505.19716","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","created":"2025-05-26","cited_by_count":15,"area":"lr"},{"id":"2511.10788","title":"From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":12,"area":"lr"},{"id":"2505.16448","title":"The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models","created":"2025-05-22","cited_by_count":10,"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":"2505.19987","title":"How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation","created":"2025-05-26","cited_by_count":5,"area":"lr"},{"id":"2509.24238","title":"Learning to Ponder: Adaptive Reasoning in Latent Space","created":"2025-09-29","cited_by_count":5,"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":"2510.15965","title":"One Token Embedding Is Enough to Deadlock Your Large Reasoning Model","created":"2025-10-12","cited_by_count":5,"area":"lr"},{"id":"2507.00045","title":"CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning","created":"2025-06-23","cited_by_count":4,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2512.21017","title":"Rethinking Supervised Fine-Tuning: Emphasizing Key Answer Tokens for Improved LLM Accuracy","created":"2025-12-24","cited_by_count":4,"area":"lr"},{"id":"2602.01472","title":"ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure","created":"2026-02-01","cited_by_count":4,"area":"lr"},{"id":"2507.13332","title":"The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner","created":"2025-07-17","cited_by_count":3,"area":"lr"},{"id":"2510.16449","title":"TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2601.03550","title":"ReEfBench: Quantifying the Reasoning Efficiency of LLMs","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2603.00578","title":"Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs","created":"2026-02-28","cited_by_count":3,"area":"lr"},{"id":"2606.11164","title":"ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2510.06101","title":"The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models","created":"2025-10-07","cited_by_count":2,"area":"lr"},{"id":"2511.03408","title":"Efficient Reasoning via Thought-Training and Thought-Free Inference","created":"2025-11-05","cited_by_count":2,"area":"lr"},{"id":"2602.12113","title":"Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2511.22176","title":"Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2601.03506","title":"QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2510.11104","title":"Enhancing LLM Reasoning via Non-Human-Like Reasoning Path Preference Optimization","created":"2025-10-13","cited_by_count":0,"area":"lr"},{"id":"2605.17037","title":"D$^2$Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning","created":"2026-05-16","cited_by_count":0,"area":"lr"},{"id":"2608.25583","title":"GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.07103","title":"Revisiting Complete Reasoning Traces for Post-Training","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.34181","title":"Efficient Reasoning via Constrained Optimization in Latent Space","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}