{"total":30,"rows":[{"id":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2505.11274","title":"SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning","created":"2025-05-16","cited_by_count":48,"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":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21,"area":"lr"},{"id":"2510.02212","title":"DiFFPO: Training Diffusion LLMs to Reason Fast and Furious via Reinforcement Learning","created":"2025-10-02","cited_by_count":19,"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":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2505.07961","title":"Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"id":"2507.15758","title":"LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization","created":"2025-07-21","cited_by_count":11,"area":"lr"},{"id":"2505.21097","title":"Thinker: Learning to Think Fast and Slow","created":"2025-05-27","cited_by_count":10,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2507.15844","title":"Hierarchical Budget Policy Optimization for Adaptive Reasoning","created":"2025-07-21","cited_by_count":8,"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":"2604.01348","title":"Procedural Knowledge at Scale Improves Reasoning","created":"2026-04-01","cited_by_count":7,"area":"lr"},{"id":"2509.25426","title":"RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2601.07036","title":"Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2604.06787","title":"When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning","created":"2026-04-08","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":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2605.03314","title":"When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning","created":"2026-05-05","cited_by_count":5,"area":"lr"},{"id":"2508.10164","title":"Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization","created":"2025-08-13","cited_by_count":3,"area":"lr"},{"id":"2510.16374","title":"Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMs","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2602.03452","title":"Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing","created":"2026-02-03","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":"2605.07686","title":"The Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output Limits","created":"2026-05-08","cited_by_count":1,"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":"2609.04947","title":"MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression","created":"2026-09-04","cited_by_count":0,"area":"lr"},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}