{"total":79,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2504.01296","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","created":"2025-04-02","cited_by_count":192,"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":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2503.04412","title":"Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search","created":"2025-03-06","cited_by_count":51,"area":"lr"},{"id":"2505.17667","title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","created":"2025-05-23","cited_by_count":50,"area":"lr"},{"id":"2504.09710","title":"DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training","created":"2025-04-13","cited_by_count":46,"area":"lr"},{"id":"2505.20315","title":"Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL","created":"2025-05-22","cited_by_count":38,"area":"lr"},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37,"area":"lr"},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35,"area":"lr"},{"id":"2507.15225","title":"Solving Formal Math Problems by Decomposition and Iterative Reflection","created":"2025-07-21","cited_by_count":35,"area":"lr"},{"id":"2506.06097","title":"VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning","created":"2025-06-06","cited_by_count":32,"area":"lr"},{"id":"2506.09513","title":"ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning","created":"2025-06-11","cited_by_count":27,"area":"lr"},{"id":"2504.10337","title":"Heimdall: test-time scaling on the generative verification","created":"2025-04-14","cited_by_count":26,"area":"lr"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2506.05566","title":"ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation","created":"2025-06-05","cited_by_count":22,"area":"lr"},{"id":"2509.26574","title":"Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark","created":"2025-09-30","cited_by_count":21,"area":"lr"},{"id":"2505.06538","title":"Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model","created":"2025-05-10","cited_by_count":19,"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":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2506.12860","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","created":"2025-06-15","cited_by_count":15,"area":"lr"},{"id":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2508.10874","title":"SSRL: Self-Search Reinforcement Learning","created":"2025-08-14","cited_by_count":14,"area":"lr"},{"id":"2511.16665","title":"Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter","created":"2025-11-20","cited_by_count":14,"area":"lr"},{"id":"2505.17373","title":"Value-Guided Search for Efficient Chain-of-Thought Reasoning","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2507.20199","title":"StepFun-Prover Preview: Let's Think and Verify Step by Step","created":"2025-07-27","cited_by_count":13,"area":"lr"},{"id":"2504.06564","title":"Thinking Out Loud: Do Reasoning Models Know When They're Right?","created":"2025-04-09","cited_by_count":12,"area":"lr"},{"id":"2508.12281","title":"Legal$\\Delta$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain","created":"2025-08-17","cited_by_count":12,"area":"lr"},{"id":"2507.00748","title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","created":"2025-07-01","cited_by_count":11,"area":"lr"},{"id":"2502.15771","title":"Learning to Reason from Feedback at Test-Time","created":"2025-02-16","cited_by_count":10,"area":"lr"},{"id":"2510.14232","title":"Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models","created":"2025-10-16","cited_by_count":10,"area":"lr"},{"id":"2511.08525","title":"Investigating CoT Monitorability in Large Reasoning Models","created":"2025-11-11","cited_by_count":9,"area":"lr"},{"id":"2511.20718","title":"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2506.18957","title":"A Comment On \"The Illusion of Thinking\": Reframing the Reasoning Cliff as an Agentic Gap","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2502.09955","title":"Diverse Inference and Verification for Advanced Reasoning","created":"2025-02-14","cited_by_count":6,"area":"lr"},{"id":"2504.02810","title":"Generative Evaluation of Complex Reasoning in Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2510.27044","title":"Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning","created":"2025-10-30","cited_by_count":6,"area":"lr"},{"id":"2601.06767","title":"GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2508.07382","title":"Pentest-R1: Towards Autonomous Penetration Testing Reasoning Optimized via Two-Stage Reinforcement Learning","created":"2025-08-10","cited_by_count":5,"area":"lr"},{"id":"2510.19429","title":"NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning","created":"2025-10-22","cited_by_count":5,"area":"lr"},{"id":"2510.03185","title":"PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning","created":"2025-10-03","cited_by_count":4,"area":"lr"},{"id":"2602.09591","title":"On the Optimal Reasoning Length for RL-Trained Language Models","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2503.23487","title":"Large Language and Reasoning Models are Shallow Disjunctive Reasoners","created":"2025-03-30","cited_by_count":3,"area":"lr"},{"id":"2505.17988","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","created":"2025-05-23","cited_by_count":3,"area":"lr"},{"id":"2510.08977","title":"Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2510.17602","title":"LexChain: Modeling Legal Reasoning Chains for Chinese Tort Case Analysis","created":"2025-10-20","cited_by_count":3,"area":"lr"},{"id":"2512.15274","title":"Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2601.20829","title":"Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2602.07848","title":"MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation","created":"2026-02-08","cited_by_count":3,"area":"lr"},{"id":"2504.01789","title":"OpenThaiGPT 1.6 and R1: Thai-Centric Open Source and Reasoning Large Language Models","created":"2025-04-02","cited_by_count":2,"area":"lr"},{"id":"2505.22068","title":"Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO","created":"2025-05-28","cited_by_count":2,"area":"lr"},{"id":"2509.06436","title":"Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning","created":"2025-09-08","cited_by_count":2,"area":"lr"},{"id":"2511.01104","title":"HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"lr"},{"id":"2511.08024","title":"Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning","created":"2025-11-11","cited_by_count":2,"area":"lr"},{"id":"2601.21711","title":"TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning","created":"2026-01-29","cited_by_count":2,"area":"lr"},{"id":"2602.04248","title":"Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2602.08693","title":"Reasoning aligns language models to human cognition","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2604.00790","title":"RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2605.06840","title":"Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2606.02218","title":"Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing","created":"2026-06-01","cited_by_count":2,"area":"lr"},{"id":"2503.18494","title":"Verbal Process Supervision Elicits Better Coding Agents","created":"2025-03-24","cited_by_count":1,"area":"lr"},{"id":"2509.03537","title":"AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models","created":"2025-08-27","cited_by_count":1,"area":"lr"},{"id":"2510.04045","title":"Exploring Chain-of-Thought Reasoning for Steerable Pluralistic Alignment","created":"2025-10-05","cited_by_count":1,"area":"lr"},{"id":"2510.08647","title":"Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2604.12379","title":"Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2607.23420","title":"LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2508.13680","title":"VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2601.12995","title":"Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models","created":"2026-01-19","cited_by_count":0,"area":"lr"},{"id":"2605.22211","title":"CLORE: Content-Level Optimization for Reasoning Efficiency","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.28713","title":"Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.16072","title":"Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D","created":"2026-07-17","cited_by_count":0,"area":"lr"},{"id":"2607.19181","title":"Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2610.18760","title":"Beyond the Verdict: Agentic Code Judging with Verifiable Feedback","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.19687","title":"Function-Space Temporal Self-Distillation for Policy Optimization","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}