{"total":76,"rows":[{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332,"area":"lr"},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203,"area":"lr"},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625,"area":"lr"},{"id":"2403.04642","title":"Teaching Large Language Models to Reason with Reinforcement Learning","created":"2024-03-07","cited_by_count":160,"area":"lr"},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156,"area":"lr"},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"area":"lr"},{"id":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2310.10080","title":"Let's reward step by step: Step-Level reward model as the Navigators for Reasoning","created":"2023-10-16","cited_by_count":102,"area":"lr"},{"id":"2502.00212","title":"STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving","created":"2025-01-31","cited_by_count":79,"area":"lr"},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"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":"2309.17272","title":"Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency","created":"2023-09-29","cited_by_count":46,"area":"lr"},{"id":"2410.08196","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","created":"2024-10-10","cited_by_count":39,"area":"lr"},{"id":"2508.15096","title":"Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset","created":"2025-08-20","cited_by_count":38,"area":"lr"},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35,"area":"lr"},{"id":"2411.04329","title":"CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models","created":"2024-11-07","cited_by_count":34,"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":"2311.06602","title":"BizBench: A Quantitative Reasoning Benchmark for Business and Finance","created":"2023-11-11","cited_by_count":28,"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":"2409.09584","title":"RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation","created":"2024-09-15","cited_by_count":26,"area":"lr"},{"id":"2402.11452","title":"AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition","created":"2024-02-18","cited_by_count":24,"area":"lr"},{"id":"2401.10695","title":"LangBridge: Multilingual Reasoning Without Multilingual Supervision","created":"2024-01-19","cited_by_count":22,"area":"lr"},{"id":"2305.19213","title":"The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code","created":"2023-05-30","cited_by_count":21,"area":"lr"},{"id":"2309.03224","title":"No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Function","created":"2023-09-01","cited_by_count":20,"area":"lr"},{"id":"2504.14363","title":"Improving RL Exploration for LLM Reasoning through Retrospective Replay","created":"2025-04-19","cited_by_count":19,"area":"lr"},{"id":"2511.20100","title":"QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation","created":"2025-11-25","cited_by_count":19,"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":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","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":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18,"area":"lr"},{"id":"2403.13271","title":"Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs","created":"2024-03-20","cited_by_count":17,"area":"lr"},{"id":"2408.07089","title":"InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning","created":"2024-08-09","cited_by_count":15,"area":"lr"},{"id":"2603.02146","title":"LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards","created":"2026-03-02","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":"2501.14002","title":"Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages","created":"2025-01-23","cited_by_count":13,"area":"lr"},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2310.04484","title":"Ada-Instruct: Adapting Instruction Generators for Complex Reasoning","created":"2023-10-06","cited_by_count":11,"area":"lr"},{"id":"2506.11027","title":"From Reasoning to Code: GRPO Optimization for Underrepresented Languages","created":"2025-05-20","cited_by_count":11,"area":"lr"},{"id":"2404.16333","title":"AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation","created":"2024-04-25","cited_by_count":10,"area":"lr"},{"id":"2510.19873","title":"From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph","created":"2025-10-22","cited_by_count":10,"area":"lr"},{"id":"2312.15960","title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","created":"2023-12-26","cited_by_count":9,"area":"lr"},{"id":"2402.10691","title":"Python is Not Always the Best Choice: Embracing Multilingual Program of Thoughts","created":"2024-02-16","cited_by_count":8,"area":"lr"},{"id":"2406.12572","title":"Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models","created":"2024-06-18","cited_by_count":8,"area":"lr"},{"id":"2410.01504","title":"PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data Augmentation","created":"2024-10-02","cited_by_count":7,"area":"lr"},{"id":"2310.10698","title":"Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation","created":"2023-10-16","cited_by_count":6,"area":"lr"},{"id":"2605.11556","title":"Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers","created":"2026-05-12","cited_by_count":5,"area":"lr"},{"id":"2603.09678","title":"EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages","created":"2026-03-10","cited_by_count":4,"area":"lr"},{"id":"2604.05868","title":"Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models","created":"2026-04-07","cited_by_count":4,"area":"lr"},{"id":"2404.07549","title":"Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective","created":"2024-04-11","cited_by_count":3,"area":"lr"},{"id":"2410.16207","title":"CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning","created":"2024-10-21","cited_by_count":3,"area":"lr"},{"id":"2410.19245","title":"MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming","created":"2024-10-25","cited_by_count":3,"area":"lr"},{"id":"2412.12544","title":"Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks","created":"2024-12-17","cited_by_count":3,"area":"lr"},{"id":"2506.09396","title":"Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models","created":"2025-06-11","cited_by_count":3,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2502.11573","title":"InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2503.12483","title":"MoT: Modularization-of-Thought Prompting for Effective Code Generation","created":"2025-03-16","cited_by_count":2,"area":"lr"},{"id":"2505.04075","title":"Rethinking LLM Advancement: Compute-Dependent and Independent Paths to Progress","created":"2025-05-07","cited_by_count":2,"area":"lr"},{"id":"2309.09809","title":"A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks","created":"2023-09-18","cited_by_count":1,"area":"lr"},{"id":"2310.16713","title":"SkyMath: Technical Report","created":"2023-10-25","cited_by_count":1,"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":"2502.15120","title":"Unveiling Reasoning Thresholds in Language Models: Scaling, Fine-Tuning, and Interpretability through Attention Maps","created":"2025-02-21","cited_by_count":1,"area":"lr"},{"id":"2508.10948","title":"Apriel-Nemotron-15B-Thinker","created":"2025-08-13","cited_by_count":1,"area":"lr"},{"id":"2510.09682","title":"Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices","created":"2025-10-08","cited_by_count":1,"area":"lr"},{"id":"2602.13962","title":"CodeGlance: Understanding Code Reasoning Challenges in LLMs through Multi-Dimensional Feature Analysis","created":"2026-02-15","cited_by_count":1,"area":"lr"},{"id":"2306.10196","title":"Structured Thoughts Automaton: First Formalized Execution Model for Auto-Regressive Language Models","created":"2023-06-16","cited_by_count":0,"area":"lr"},{"id":"2410.07062","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","created":"2024-10-09","cited_by_count":0,"area":"lr"},{"id":"2509.15690","title":"CCrepairBench: A High-Fidelity Benchmark and Reinforcement Learning Framework for C++ Compilation Repair","created":"2025-09-19","cited_by_count":0,"area":"lr"},{"id":"2510.17598","title":"Reasoning Distillation and Structural Alignment for Improved Code Generation","created":"2025-10-20","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":"2601.21469","title":"Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.04919","title":"Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2603.23470","title":"ConceptCoder: Improve Code Reasoning via Concept Learning","created":"2026-03-24","cited_by_count":0,"area":"lr"}],"next_cursor":null}