{"total":18,"rows":[{"id":"2510.08731","title":"When to Reason: Semantic Router for vLLM","created":"2025-10-09","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":"2604.27998","title":"Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning","created":"2026-04-30","cited_by_count":10,"area":"lr"},{"id":"2602.09953","title":"ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning","created":"2026-02-10","cited_by_count":9,"area":"lr"},{"id":"2602.10520","title":"Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models","created":"2026-02-11","cited_by_count":8,"area":"lr"},{"id":"2605.17672","title":"Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models","created":"2026-05-17","cited_by_count":7,"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":"2601.05693","title":"Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models","created":"2026-01-09","cited_by_count":5,"area":"lr"},{"id":"2602.10004","title":"ESTAR: Early-Stopping Token-Aware Reasoning For Efficient Inference","created":"2026-02-10","cited_by_count":3,"area":"lr"},{"id":"2605.14619","title":"SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning","created":"2026-05-14","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":"2511.04108","title":"Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2605.13165","title":"STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.30832","title":"SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.17890","title":"Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2607.20129","title":"CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2607.08196","title":"A First-Principles Theory of Slow Thinking and Active Perception","created":"2026-07-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}