{"total":31,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"area":"lr"},{"id":"2508.15260","title":"Deep Think with Confidence","created":"2025-08-21","cited_by_count":205,"area":"lr"},{"id":"2504.09858","title":"Reasoning Models Can Be Effective Without Thinking","created":"2025-04-14","cited_by_count":187,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2505.15400","title":"When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning","created":"2025-05-21","cited_by_count":26,"area":"lr"},{"id":"2505.12284","title":"Shorten After You're Right: Lazy Length Penalties for Reasoning RL","created":"2025-05-18","cited_by_count":25,"area":"lr"},{"id":"2506.02678","title":"TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression","created":"2025-06-03","cited_by_count":16,"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":"2511.06190","title":"Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning","created":"2025-11-09","cited_by_count":9,"area":"lr"},{"id":"2601.21418","title":"Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"lr"},{"id":"2603.14251","title":"Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2604.12632","title":"Calibration-Aware Policy Optimization for Reasoning LLMs","created":"2026-04-14","cited_by_count":5,"area":"lr"},{"id":"2508.15507","title":"Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning","created":"2025-08-21","cited_by_count":3,"area":"lr"},{"id":"2509.23633","title":"Fast Thinking for Large Language Models","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2510.21007","title":"Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2605.25244","title":"Inference Time Optimization with Confidence Dynamics","created":"2026-05-24","cited_by_count":2,"area":"lr"},{"id":"2608.21860","title":"ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning","created":"2026-08-22","cited_by_count":1,"area":"lr"},{"id":"2510.06750","title":"Gold-Switch: Training-Free Superposition of Slow- and Fast- Thinking LLMs","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2604.16535","title":"SCATR: Simple Calibrated Test-Time Ranking","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2605.01749","title":"Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality","created":"2026-05-03","cited_by_count":0,"area":"lr"},{"id":"2606.30217","title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2608.10441","title":"Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.15817","title":"RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2609.33970","title":"On the Token Value Inequality in Efficient Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34572","title":"Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34857","title":"Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.07716","title":"Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}