{"total":66,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132,"area":"lr"},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442,"area":"lr"},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"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":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332,"area":"lr"},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076,"area":"lr"},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988,"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":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247,"area":"lr"},{"id":"2405.11403","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","created":"2024-05-18","cited_by_count":177,"area":"lr"},{"id":"2407.18219","title":"Recursive Introspection: Teaching Language Model Agents How to Self-Improve","created":"2024-07-25","cited_by_count":165,"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":"2312.04474","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","created":"2023-12-07","cited_by_count":123,"area":"lr"},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"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":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70,"area":"lr"},{"id":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64,"area":"lr"},{"id":"2405.13144","title":"LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages","created":"2024-05-21","cited_by_count":49,"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":"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":"2306.00108","title":"Better patching using LLM prompting, via Self-Consistency","created":"2023-05-31","cited_by_count":29,"area":"lr"},{"id":"2308.08784","title":"CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation","created":"2023-08-17","cited_by_count":29,"area":"lr"},{"id":"2306.02797","title":"Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language","created":"2023-06-05","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":"2509.26314","title":"Latent Thinking Optimization: Your Latent Reasoning Language Model Secretly Encodes Reward Signals in Its Latent Thoughts","created":"2025-09-30","cited_by_count":19,"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":"2404.01226","title":"Stable Code Technical Report","created":"2024-04-01","cited_by_count":16,"area":"lr"},{"id":"2509.13351","title":"Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning","created":"2025-09-14","cited_by_count":15,"area":"lr"},{"id":"2405.17057","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation","created":"2024-05-27","cited_by_count":14,"area":"lr"},{"id":"2408.08302","title":"Benchmarking the Capabilities of Large Language Models in Transportation System Engineering: Accuracy, Consistency, and Reasoning Behaviors","created":"2024-08-15","cited_by_count":13,"area":"lr"},{"id":"2304.01665","title":"Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks","created":"2023-04-04","cited_by_count":12,"area":"lr"},{"id":"2305.18170","title":"Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning","created":"2023-05-29","cited_by_count":11,"area":"lr"},{"id":"2403.07747","title":"FineMath: A Fine-Grained Mathematical Evaluation Benchmark for Chinese Large Language Models","created":"2024-03-12","cited_by_count":10,"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":"2506.15695","title":"SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models","created":"2025-05-28","cited_by_count":8,"area":"lr"},{"id":"2508.05954","title":"Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents","created":"2025-08-08","cited_by_count":8,"area":"lr"},{"id":"2410.11900","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","created":"2024-10-14","cited_by_count":7,"area":"lr"},{"id":"2503.23314","title":"SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science","created":"2025-03-30","cited_by_count":7,"area":"lr"},{"id":"2506.18485","title":"A Simple \"Motivation\" Can Enhance Reinforcement Finetuning of Large Reasoning Models","created":"2025-06-23","cited_by_count":7,"area":"lr"},{"id":"2309.16436","title":"Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving","created":"2023-09-28","cited_by_count":6,"area":"lr"},{"id":"2505.19405","title":"CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems","created":"2025-05-26","cited_by_count":4,"area":"lr"},{"id":"2507.03051","title":"Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization","created":"2025-07-03","cited_by_count":4,"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":"2410.23402","title":"VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning","created":"2024-10-30","cited_by_count":3,"area":"lr"},{"id":"2502.18487","title":"AuPair: Golden Example Pairs for Code Repair","created":"2025-02-12","cited_by_count":3,"area":"lr"},{"id":"2604.02621","title":"Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge","created":"2026-04-03","cited_by_count":3,"area":"lr"},{"id":"2606.16222","title":"Latent Thought Flow: Efficient Latent Reasoning in Large Language Models","created":"2026-06-15","cited_by_count":3,"area":"lr"},{"id":"2502.11901","title":"Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity","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":"2506.03921","title":"Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning","created":"2025-06-04","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":"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":"2505.05756","title":"Evolutionary thoughts: integration of large language models and evolutionary algorithms","created":"2025-05-09","cited_by_count":1,"area":"lr"},{"id":"2506.07664","title":"Synthesis by Design: Controlled Data Generation via Structural Guidance","created":"2025-06-09","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":"2606.24124","title":"VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2505.06321","title":"Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning","created":"2025-05-09","cited_by_count":0,"area":"lr"},{"id":"2509.05553","title":"Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study","created":"2025-09-06","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":"2601.01931","title":"D\\'ej\\`aQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems","created":"2026-01-05","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":"2607.20908","title":"Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation","created":"2026-07-23","cited_by_count":0,"area":"lr"}],"next_cursor":null}