{"total":34,"rows":[{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75,"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":"2509.26522","title":"Entropy After </Think> for reasoning model early exiting","created":"2025-09-30","cited_by_count":24,"area":"lr"},{"id":"2510.08146","title":"Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning","created":"2025-10-09","cited_by_count":24,"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":"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":"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":"2602.03814","title":"Conformal Thinking: Risk Control for Reasoning on a Compute Budget","created":"2026-02-03","cited_by_count":10,"area":"lr"},{"id":"2605.08083","title":"LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling","created":"2026-05-08","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":"2601.23163","title":"Probing the Trajectories of Reasoning Traces in Large Language Models","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2603.12529","title":"TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning","created":"2026-03-13","cited_by_count":6,"area":"lr"},{"id":"2604.04930","title":"Early Stopping for Large Reasoning Models via Confidence Dynamics","created":"2026-04-06","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":"2511.02130","title":"Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning","created":"2025-11-03","cited_by_count":4,"area":"lr"},{"id":"2512.17901","title":"When Reasoning Meets Its Laws","created":"2025-12-19","cited_by_count":3,"area":"lr"},{"id":"2601.03649","title":"SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2602.02010","title":"NEAT: Neuron-Based Early Exit for Large Reasoning Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2604.17304","title":"Efficient Test-Time Scaling via Temporal Reasoning Aggregation","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2604.07922","title":"SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2605.27965","title":"The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.03102","title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2608.29988","title":"AutoCRAT: Within-trajectory Joint Control of Stochasticity and Compute for LLM Reasoning","created":"2026-08-30","cited_by_count":2,"area":"lr"},{"id":"2509.24957","title":"Intra-request branch orchestration for efficient LLM reasoning","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2604.09150","title":"Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2608.16425","title":"ParaTempo: Efficient Parallel Reasoning via Temporal Confidence","created":"2026-08-17","cited_by_count":1,"area":"lr"},{"id":"2608.27963","title":"SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing","created":"2026-08-28","cited_by_count":1,"area":"lr"},{"id":"2606.07968","title":"RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks","created":"2026-06-06","cited_by_count":0,"area":"lr"},{"id":"2607.11089","title":"OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2609.16055","title":"State of Thought Enables Endogenous Reasoning","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.31619","title":"Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.37304","title":"MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38997","title":"Settle: Learning When to Stop Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}