{"total":31,"rows":[{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"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":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"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":"2505.18822","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","created":"2025-05-24","cited_by_count":50,"area":"lr"},{"id":"2602.13517","title":"Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens","created":"2026-02-13","cited_by_count":22,"area":"lr"},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","cited_by_count":19,"area":"lr"},{"id":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","cited_by_count":19,"area":"lr"},{"id":"2509.06861","title":"Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet","created":"2025-09-08","cited_by_count":11,"area":"lr"},{"id":"2510.10494","title":"Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning","created":"2025-10-12","cited_by_count":9,"area":"lr"},{"id":"2504.11239","title":"Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs","created":"2025-04-15","cited_by_count":7,"area":"lr"},{"id":"2510.15987","title":"AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2509.20868","title":"StyleBench: Evaluating thinking styles in Large Language Models","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2506.13102","title":"Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2508.08115","title":"TeamMedAgents: Pareto-Efficient Multi-Agent Medical Reasoning Through Teamwork Theory","created":"2025-08-11","cited_by_count":1,"area":"lr"},{"id":"2509.17177","title":"FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions","created":"2025-09-21","cited_by_count":1,"area":"lr"},{"id":"2510.06014","title":"ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models","created":"2025-10-07","cited_by_count":1,"area":"lr"},{"id":"2510.10293","title":"MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning","created":"2025-10-11","cited_by_count":1,"area":"lr"},{"id":"2512.11213","title":"FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration","created":"2025-12-12","cited_by_count":1,"area":"lr"},{"id":"2604.00890","title":"Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2606.00376","title":"The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.31484","title":"Fork-Think with Confidence","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2508.13654","title":"Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2604.00438","title":"TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2605.06219","title":"Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2607.19932","title":"Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.14927","title":"LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2608.17414","title":"REChart: Reasoning-Efficient Chart Editing with Large Reasoning Models","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2610.11223","title":"SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.18583","title":"Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}