{"total":98,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203,"area":"lr"},{"id":"2503.10615","title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","created":"2025-03-13","cited_by_count":370,"area":"lr"},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2502.18581","title":"Scalable Best-of-N Selection for Large Language Models via Self-Certainty","created":"2025-02-25","cited_by_count":187,"area":"lr"},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98,"area":"lr"},{"id":"2506.14965","title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","created":"2025-06-17","cited_by_count":76,"area":"lr"},{"id":"2502.00674","title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","created":"2025-02-02","cited_by_count":54,"area":"lr"},{"id":"2502.02508","title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","created":"2025-02-04","cited_by_count":53,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2403.16437","title":"Reasoning Runtime Behavior of a Program with LLM: How Far Are We?","created":"2024-03-25","cited_by_count":45,"area":"lr"},{"id":"2505.15034","title":"RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning","created":"2025-05-21","cited_by_count":40,"area":"lr"},{"id":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2506.14755","title":"Optimizing Length Compression in Large Reasoning Models","created":"2025-06-17","cited_by_count":38,"area":"lr"},{"id":"2402.09664","title":"CodeMind: Evaluating Large Language Models for Code Reasoning","created":"2024-02-15","cited_by_count":32,"area":"lr"},{"id":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31,"area":"lr"},{"id":"2505.15431","title":"Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought","created":"2025-05-21","cited_by_count":29,"area":"lr"},{"id":"2406.01006","title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","created":"2024-06-03","cited_by_count":27,"area":"lr"},{"id":"2502.12466","title":"EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking","created":"2025-02-18","cited_by_count":24,"area":"lr"},{"id":"2403.17218","title":"To Err is Machine: Vulnerability Detection Challenges LLM Reasoning","created":"2024-03-25","cited_by_count":18,"area":"lr"},{"id":"2410.01999","title":"CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs","created":"2024-10-02","cited_by_count":18,"area":"lr"},{"id":"2503.23145","title":"CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis","created":"2025-03-29","cited_by_count":16,"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":"2506.00750","title":"CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning","created":"2025-05-31","cited_by_count":13,"area":"lr"},{"id":"2409.19381","title":"HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning","created":"2024-09-28","cited_by_count":11,"area":"lr"},{"id":"2506.15455","title":"RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation","created":"2025-06-18","cited_by_count":11,"area":"lr"},{"id":"2506.11480","title":"LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment","created":"2025-06-13","cited_by_count":9,"area":"lr"},{"id":"2507.16518","title":"SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning","created":"2025-07-22","cited_by_count":8,"area":"lr"},{"id":"2510.26143","title":"Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math","created":"2025-10-30","cited_by_count":8,"area":"lr"},{"id":"2411.03471","title":"MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs","created":"2024-11-05","cited_by_count":7,"area":"lr"},{"id":"2501.18482","title":"A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models","created":"2025-01-30","cited_by_count":7,"area":"lr"},{"id":"2507.17307","title":"R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning","created":"2025-07-23","cited_by_count":7,"area":"lr"},{"id":"2502.13170","title":"Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment","created":"2025-02-17","cited_by_count":6,"area":"lr"},{"id":"2510.03415","title":"LLMs Lean on Priors, Not Programming Language Semantics","created":"2025-10-03","cited_by_count":6,"area":"lr"},{"id":"2601.03731","title":"From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level","created":"2026-01-07","cited_by_count":6,"area":"lr"},{"id":"2603.11226","title":"ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning","created":"2026-03-11","cited_by_count":6,"area":"lr"},{"id":"2603.16475","title":"Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2508.20373","title":"NPG-Muse: Scaling Long Chain-of-Thought Reasoning with NP-Hard Graph Problems","created":"2025-08-28","cited_by_count":5,"area":"lr"},{"id":"2512.00215","title":"Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation","created":"2025-11-28","cited_by_count":5,"area":"lr"},{"id":"2512.02914","title":"Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2607.25996","title":"RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models","created":"2026-07-28","cited_by_count":5,"area":"lr"},{"id":"2504.01935","title":"Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length?","created":"2025-04-02","cited_by_count":4,"area":"lr"},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2507.17548","title":"CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning","created":"2025-07-23","cited_by_count":4,"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":"2509.26546","title":"Towards Verified Code Reasoning by LLMs","created":"2025-09-30","cited_by_count":4,"area":"lr"},{"id":"2602.04288","title":"Contextual Drag: How Errors in the Context Affect LLM Reasoning","created":"2026-02-04","cited_by_count":4,"area":"lr"},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2605.22217","title":"Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2507.07498","title":"Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code","created":"2025-07-10","cited_by_count":3,"area":"lr"},{"id":"2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2510.11457","title":"From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2512.14917","title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","created":"2025-12-16","cited_by_count":3,"area":"lr"},{"id":"2507.15378","title":"AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming","created":"2025-07-21","cited_by_count":2,"area":"lr"},{"id":"2511.00488","title":"\\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2604.25399","title":"CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2605.29277","title":"Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.24437","title":"ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling","created":"2026-06-23","cited_by_count":2,"area":"lr"},{"id":"2607.21981","title":"J-CoT: Chain-of-Thought in J-Space","created":"2026-07-24","cited_by_count":2,"area":"lr"},{"id":"2412.12163","title":"Towards LLM-based optimization compilers. Can LLMs learn how to apply a single peephole optimization? Reasoning is all LLMs need!","created":"2024-12-11","cited_by_count":1,"area":"lr"},{"id":"2507.14849","title":"Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding","created":"2025-07-20","cited_by_count":1,"area":"lr"},{"id":"2508.05193","title":"STEPWISE-CODEX-Bench: Evaluating Complex Multi-Function Comprehension and Fine-Grained Execution Reasoning","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2511.02197","title":"Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs","created":"2025-11-04","cited_by_count":1,"area":"lr"},{"id":"2602.18806","title":"Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models","created":"2026-02-21","cited_by_count":1,"area":"lr"},{"id":"2603.14628","title":"s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs","created":"2026-03-15","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":"2604.16931","title":"Playing Psychic: Using Thought Trees to Predict Reasoning Models Accuracy on Coding Tasks","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.17290","title":"Probabilistic Programs of Thought","created":"2026-04-19","cited_by_count":1,"area":"lr"},{"id":"2604.25419","title":"JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2605.07353","title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.11006","title":"An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning","created":"2026-05-10","cited_by_count":1,"area":"lr"},{"id":"2605.17958","title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2605.18851","title":"STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2606.05145","title":"Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2608.03119","title":"Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2505.17481","title":"MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning","created":"2025-05-23","cited_by_count":0,"area":"lr"},{"id":"2512.00127","title":"Generating Verifiable Chain of Thoughts from Exection-Traces","created":"2025-11-28","cited_by_count":0,"area":"lr"},{"id":"2601.10274","title":"Queueing-Aware Optimization of Reasoning Tokens for Accuracy-Latency Trade-offs in LLM Servers","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2602.18905","title":"TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning","created":"2026-02-21","cited_by_count":0,"area":"lr"},{"id":"2603.19558","title":"TextReasoningBench: Does Reasoning Really Improve Text Classification in Large Language Models?","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2604.12881","title":"Evaluating LLMs Code Reasoning Under Real-World Context","created":"2026-04-14","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":"2605.22620","title":"Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework","created":"2026-05-21","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":"2608.03388","title":"Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2609.16076","title":"The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.28449","title":"Can LLMs Reason About Runtime Behavior? A Repository-Level Dynamic Benchmark","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.34661","title":"Codoku: Renewable Program-Reasoning Challenges for Frontier Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.37169","title":"Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38137","title":"LongHarness Bench: Stress-Testing Language Model Harnesses for Long-Context Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38829","title":"Diversity Combining for Multi-Path LLM Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.05472","title":"Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.18755","title":"PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}