{"total":92,"rows":[{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203,"area":"lr"},{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415,"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":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"area":"lr"},{"id":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158,"area":"lr"},{"id":"2601.03192","title":"MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory","created":"2026-01-06","cited_by_count":129,"area":"lr"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93,"area":"lr"},{"id":"2505.23575","title":"CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring","created":"2025-05-29","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":"2506.12286","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","created":"2025-06-14","cited_by_count":49,"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":"2506.08745","title":"Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":46,"area":"lr"},{"id":"2502.19361","title":"Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?","created":"2025-02-26","cited_by_count":44,"area":"lr"},{"id":"2504.15253","title":"Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators","created":"2025-04-21","cited_by_count":44,"area":"lr"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2502.12468","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation","created":"2025-02-18","cited_by_count":32,"area":"lr"},{"id":"2501.14275","title":"Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation","created":"2025-01-24","cited_by_count":29,"area":"lr"},{"id":"2508.05170","title":"ReCode: Reinforcing Code Generation with Reasoning-Process Rewards","created":"2025-08-07","cited_by_count":25,"area":"lr"},{"id":"2410.18693","title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","created":"2024-10-24","cited_by_count":24,"area":"lr"},{"id":"2505.02881","title":"Rewriting Pre-Training Data Boosts LLM Performance in Math and Code","created":"2025-05-05","cited_by_count":21,"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":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2506.04592","title":"Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification","created":"2025-06-05","cited_by_count":17,"area":"lr"},{"id":"2510.23038","title":"Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning","created":"2025-10-27","cited_by_count":17,"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":"2502.13389","title":"Reasoning with Reinforced Functional Token Tuning","created":"2025-02-19","cited_by_count":14,"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":"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":"2511.01758","title":"RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks","created":"2025-11-03","cited_by_count":13,"area":"lr"},{"id":"2503.10061","title":"Compute Optimal Scaling of Skills: Knowledge vs Reasoning","created":"2025-03-13","cited_by_count":11,"area":"lr"},{"id":"2504.19093","title":"CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges","created":"2025-04-27","cited_by_count":11,"area":"lr"},{"id":"2501.18858","title":"BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning","created":"2025-01-31","cited_by_count":10,"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":"2605.16986","title":"Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents","created":"2026-05-16","cited_by_count":10,"area":"lr"},{"id":"2502.09183","title":"RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation","created":"2025-02-13","cited_by_count":8,"area":"lr"},{"id":"2502.15835","title":"Pragmatic Reasoning improves LLM Code Generation","created":"2025-02-20","cited_by_count":7,"area":"lr"},{"id":"2504.04699","title":"R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation","created":"2025-04-07","cited_by_count":7,"area":"lr"},{"id":"2509.22824","title":"Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2512.23631","title":"BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2412.02906","title":"Does Few-Shot Learning Help LLM Performance in Code Synthesis?","created":"2024-12-03","cited_by_count":6,"area":"lr"},{"id":"2502.10742","title":"The Philosophical Foundations of Growing AI Like A Child","created":"2025-02-15","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":"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":"2503.22832","title":"L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution","created":"2025-03-28","cited_by_count":5,"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":"2512.03176","title":"Plantain: Plan-Answer Interleaved Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2504.11364","title":"Offline Learning and Forgetting for Reasoning with Large Language Models","created":"2025-04-15","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":"2509.14760","title":"Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2511.15392","title":"DEPO: Dual-Efficiency Preference Optimization for LLM Agents","created":"2025-11-19","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":"2506.00845","title":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2506.18421","title":"TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models","created":"2025-06-23","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":"2601.18832","title":"The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2601.22249","title":"FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2603.01563","title":"LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2604.26102","title":"SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent","created":"2026-04-28","cited_by_count":3,"area":"lr"},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2511.05874","title":"An Empirical Study of Reasoning Steps in Thinking Code LLMs","created":"2025-11-08","cited_by_count":2,"area":"lr"},{"id":"2512.09679","title":"Understanding Chain-of-Thought Effectiveness in Code Generation: An Empirical and Information-Theoretic Analysis","created":"2025-12-10","cited_by_count":2,"area":"lr"},{"id":"2604.18364","title":"Training and Agentic Inference Strategies for LLM-based Manim Animation Generation","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.28182","title":"Exploration Hacking: Can LLMs Learn to Resist RL Training?","created":"2026-04-30","cited_by_count":2,"area":"lr"},{"id":"2607.02436","title":"Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study","created":"2026-07-02","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":"2509.19893","title":"Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning","created":"2025-09-24","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":"2601.22230","title":"DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code Generation","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2603.01571","title":"Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models","created":"2026-03-02","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":"2606.08974","title":"Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"id":"2512.06859","title":"JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models","created":"2025-12-07","cited_by_count":0,"area":"lr"},{"id":"2603.17815","title":"Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2603.18334","title":"Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.12214","title":"Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code","created":"2026-04-14","cited_by_count":0,"area":"lr"},{"id":"2604.26173","title":"Entropy Centroids as Intrinsic Rewards for Test-Time Scaling","created":"2026-04-28","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":"2607.07619","title":"Rethinking Code Performance Benchmarks for LLMs","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2608.10928","title":"ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.29632","title":"InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information","created":"2026-08-30","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":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.12872","title":"Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13594","title":"MENTOR: Learning from Failure with On-Policy Pedagogical Intervention","created":"2026-10-09","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}