{"total":37,"rows":[{"id":"2506.15674","title":"Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers","created":"2025-06-18","cited_by_count":28,"area":"lr"},{"id":"2505.17941","title":"VeriThinker: Learning to Verify Makes Reasoning Model Efficient","created":"2025-05-23","cited_by_count":24,"area":"lr"},{"id":"2506.09853","title":"Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning","created":"2025-06-11","cited_by_count":17,"area":"lr"},{"id":"2505.14216","title":"Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning","created":"2025-05-20","cited_by_count":14,"area":"lr"},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2507.06607","title":"Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation","created":"2025-07-09","cited_by_count":11,"area":"lr"},{"id":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2608.04001","title":"Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2505.14147","title":"SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning","created":"2025-05-20","cited_by_count":5,"area":"lr"},{"id":"2510.10013","title":"Path Drift in Large Reasoning Models:How First-Person Commitments Override Safety","created":"2025-10-11","cited_by_count":5,"area":"lr"},{"id":"2510.15965","title":"One Token Embedding Is Enough to Deadlock Your Large Reasoning Model","created":"2025-10-12","cited_by_count":5,"area":"lr"},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2505.13718","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2508.16677","title":"Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration","created":"2025-08-21","cited_by_count":3,"area":"lr"},{"id":"2509.23746","title":"Poivre: Self-Refining Visual Pointing with Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"id":"2509.25810","title":"Learning to Reason as Action Abstractions with Scalable Mid-Training RL","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2510.10168","title":"Concise Reasoning in the Lens of Lagrangian Optimization","created":"2025-10-11","cited_by_count":3,"area":"lr"},{"id":"2512.17901","title":"When Reasoning Meets Its Laws","created":"2025-12-19","cited_by_count":3,"area":"lr"},{"id":"2603.13274","title":"Learning from Partial Chain-of-Thought via Truncated-Reasoning Self-Distillation","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2509.22230","title":"In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2510.11031","title":"LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2510.16259","title":"Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense","created":"2025-10-17","cited_by_count":2,"area":"lr"},{"id":"2601.21000","title":"UrduBench: An Urdu Reasoning Benchmark using Contextually Ensembled Translations with Human-in-the-Loop","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2604.12229","title":"HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models","created":"2026-04-14","cited_by_count":2,"area":"lr"},{"id":"2604.15490","title":"Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch","created":"2026-04-16","cited_by_count":2,"area":"lr"},{"id":"2506.08625","title":"RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval","created":"2025-06-10","cited_by_count":1,"area":"lr"},{"id":"2508.18743","title":"CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2601.07790","title":"Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2601.21600","title":"CORE: Collaborative Reasoning via Cross Teaching","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.15332","title":"Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2605.29247","title":"DenseSteer: Steering Small Language Models towards Dense Math Reasoning","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2507.04142","title":"Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies","created":"2025-07-05","cited_by_count":0,"area":"lr"},{"id":"2601.03268","title":"WRAVAL -- WRiting Assist eVALuation","created":"2025-12-19","cited_by_count":0,"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":"2603.16867","title":"Efficient Reasoning on the Edge","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2606.17024","title":"ExpRL: Exploratory RL for LLM Mid-Training","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2608.06347","title":"RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer","created":"2026-08-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}