{"total":47,"rows":[{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2509.19284","title":"What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT","created":"2025-09-23","cited_by_count":25,"area":"lr"},{"id":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"area":"lr"},{"id":"2510.07300","title":"Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2507.12428","title":"Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models","created":"2025-07-16","cited_by_count":17,"area":"lr"},{"id":"2507.17512","title":"Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning","created":"2025-07-23","cited_by_count":17,"area":"lr"},{"id":"2510.08308","title":"First Try Matters: Revisiting the Role of Reflection in Reasoning Models","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2507.14783","title":"Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling","created":"2025-07-20","cited_by_count":10,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2605.17497","title":"Self-Supervised On-Policy Distillation for Reasoning Language Models","created":"2026-05-17","cited_by_count":10,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2604.26573","title":"PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners","created":"2026-04-29","cited_by_count":8,"area":"lr"},{"id":"2510.11713","title":"Are Large Reasoning Models Interruptible?","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2602.14763","title":"Unlocking Reasoning Capability on Machine Translation in Large Language Models","created":"2026-02-16","cited_by_count":6,"area":"lr"},{"id":"2603.20508","title":"Measuring Weak-to-Strong Legibility of Reasoning Models","created":"2026-03-20","cited_by_count":5,"area":"lr"},{"id":"2604.12378","title":"ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance","created":"2026-04-14","cited_by_count":5,"area":"lr"},{"id":"2509.24147","title":"Your thoughts tell who you are: Characterize the reasoning patterns of LRMs","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2509.22193","title":"Scale or Reason? A Compute-Equivalent Analysis of Reasoning Distillation","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2512.05962","title":"Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2603.20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","created":"2026-03-20","cited_by_count":3,"area":"lr"},{"id":"2508.03979","title":"Confidence-Weighted Token Set Cover for Early Hypothesis Pruning in Self-Consistency","created":"2025-08-06","cited_by_count":2,"area":"lr"},{"id":"2511.01937","title":"Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR","created":"2025-11-02","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":"2604.21593","title":"Language as a Latent Variable for Reasoning Optimization","created":"2026-04-23","cited_by_count":2,"area":"lr"},{"id":"2607.00485","title":"Efficient Multilingual Reasoning Transfer via Progressive Code-Switching","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2507.07328","title":"Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery","created":"2025-07-09","cited_by_count":1,"area":"lr"},{"id":"2604.09338","title":"Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2604.17957","title":"Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.04330","title":"The Scaling Properties of Implicit Deductive Reasoning in Transformers","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2607.10114","title":"Cost of Reasoning in non-English Languages: A Case Study on Japanese","created":"2026-07-11","cited_by_count":1,"area":"lr"},{"id":"2508.13382","title":"Datarus-R1: An Adaptive Multi-Step Reasoning LLM for Automated Data Analysis","created":"2025-08-18","cited_by_count":0,"area":"lr"},{"id":"2510.24150","title":"Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2603.01214","title":"Reasoning Boosts Opinion Alignment in LLMs","created":"2026-03-01","cited_by_count":0,"area":"lr"},{"id":"2603.18256","title":"MolRGen: A Training and Evaluation Setting for De Novo Molecular Generation with Reasonning Models","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.20917","title":"The Path Not Taken: Duality in Reasoning about Program Execution","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2604.23813","title":"ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction","created":"2026-04-26","cited_by_count":0,"area":"lr"},{"id":"2605.20201","title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2605.23926","title":"How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2606.08436","title":"CACR:Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2606.15080","title":"AdaMame: A Training Recipe for Adaptive Multilingual Reasoning","created":"2026-06-13","cited_by_count":0,"area":"lr"},{"id":"2609.10445","title":"Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}