{"total":200,"rows":[{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442,"area":"lr"},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462,"area":"lr"},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183,"area":null},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106,"area":null},{"id":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63,"area":"lr"},{"id":"2108.11590","title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","created":"2021-08-26","cited_by_count":59,"area":null},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57,"area":null},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"id":"2503.11576","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","created":"2025-03-14","cited_by_count":53,"area":"mllm"},{"id":"2504.12522","title":"Evaluating the Diversity and Quality of LLM Generated Content","created":"2025-04-16","cited_by_count":51,"area":"lr"},{"id":"2407.21579","title":"A Performance Study of LLM-Generated Code on Leetcode","created":"2024-07-31","cited_by_count":49,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2305.05383","title":"Code Execution with Pre-trained Language Models","created":"2023-05-08","cited_by_count":34,"area":null},{"id":"2407.07064","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","created":"2024-07-09","cited_by_count":34,"area":null},{"id":"2410.15756","title":"Automated Proof Generation for Rust Code via Self-Evolution","created":"2024-10-21","cited_by_count":33,"area":null},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32,"area":null},{"id":"2306.03438","title":"Large Language Models of Code Fail at Completing Code with Potential Bugs","created":"2023-06-06","cited_by_count":29,"area":null},{"id":"2406.11698","title":"Meta Reasoning for Large Language Models","created":"2024-06-17","cited_by_count":29,"area":"lr"},{"id":"2311.11690","title":"Refactoring Programs Using Large Language Models with Few-Shot Examples","created":"2023-11-20","cited_by_count":28,"area":null},{"id":"2408.12159","title":"Search-Based LLMs for Code Optimization","created":"2024-08-22","cited_by_count":28,"area":null},{"id":"2407.14044","title":"ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?","created":"2024-07-19","cited_by_count":27,"area":null},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"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":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"area":null},{"id":"2404.03543","title":"CodeEditorBench: Evaluating Code Editing Capability of Large Language Models","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2412.17744","title":"RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation","created":"2024-12-23","cited_by_count":23,"area":null},{"id":"2406.14408","title":"FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving","created":"2024-06-20","cited_by_count":22,"area":null},{"id":"2407.07472","title":"Rectifier: Code Translation with Corrector via LLMs","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2505.19997","title":"Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents","created":"2025-05-26","cited_by_count":19,"area":"agents"},{"id":"2506.14683","title":"Unified Software Engineering Agent as AI Software Engineer","created":"2025-06-17","cited_by_count":19,"area":"agents"},{"id":"2210.01185","title":"ContraCLM: Contrastive Learning For Causal Language Model","created":"2022-10-03","cited_by_count":18,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"id":"2206.07796","title":"FixEval: Execution-based Evaluation of Program Fixes for Programming Problems","created":"2022-06-15","cited_by_count":17,"area":null},{"id":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2308.13490","title":"TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs","created":"2023-08-25","cited_by_count":16,"area":null},{"id":"2309.14846","title":"Supersonic: Learning to Generate Source Code Optimizations in C/C++","created":"2023-09-26","cited_by_count":16,"area":null},{"id":"2411.01063","title":"InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"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":"2402.14558","title":"LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Survey","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2403.16702","title":"ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2203.03771","title":"Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2304.01102","title":"RunBugRun -- An Executable Dataset for Automated Program Repair","created":"2023-04-03","cited_by_count":11,"area":null},{"id":"2307.07686","title":"Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++","created":"2023-07-15","cited_by_count":11,"area":null},{"id":"2503.12029","title":"Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks","created":"2025-03-15","cited_by_count":11,"area":"agents"},{"id":"2505.04441","title":"Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2509.26476","title":"Regression Language Models for Code","created":"2025-09-30","cited_by_count":11,"area":null},{"id":"2310.11476","title":"Program Translation via Code Distillation","created":"2023-10-17","cited_by_count":10,"area":"mechinterp"},{"id":"2405.20252","title":"Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimization","created":"2024-05-30","cited_by_count":10,"area":"agents"},{"id":"2212.10017","title":"Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities","created":"2022-12-20","cited_by_count":9,"area":null},{"id":"2311.00317","title":"Data Augmentation for Code Translation with Comparable Corpora and Multiple References","created":"2023-11-01","cited_by_count":9,"area":null},{"id":"2401.03855","title":"PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2403.17214","title":"Output Format Biases in the Evaluation of Large Language Models for Code Translation","created":"2024-03-25","cited_by_count":9,"area":null},{"id":"2503.12511","title":"SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification","created":"2025-03-16","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2507.10583","title":"$\\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection","created":"2025-07-11","cited_by_count":9,"area":null},{"id":"2309.09980","title":"Code Representation Pre-training with Complements from Program Executions","created":"2023-09-04","cited_by_count":8,"area":null},{"id":"2312.05657","title":"PerfRL: A Small Language Model Framework for Efficient Code Optimization","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2406.06559","title":"Harnessing Business and Media Insights with Large Language Models","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2409.04183","title":"GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding","created":"2024-09-06","cited_by_count":7,"area":"alignment"},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2204.08653","title":"On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2206.05480","title":"CodeS: Towards Code Model Generalization Under Distribution Shift","created":"2022-06-11","cited_by_count":6,"area":null},{"id":"2208.08643","title":"Learning Program Representations with a Tree-Structured Transformer","created":"2022-08-18","cited_by_count":6,"area":null},{"id":"2404.08885","title":"Is Next Token Prediction Sufficient for GPT? Exploration on Code Logic Comprehension","created":"2024-04-13","cited_by_count":6,"area":null},{"id":"2408.04660","title":"XMainframe: A Large Language Model for Mainframe Modernization","created":"2024-08-05","cited_by_count":6,"area":null},{"id":"2409.15395","title":"Parse Trees Guided LLM Prompt Compression","created":"2024-09-23","cited_by_count":6,"area":"inference"},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2506.11066","title":"CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2603.16011","title":"FormulaCode: Evaluating Agentic Optimization on Large Codebases","created":"2026-03-16","cited_by_count":6,"area":"agents"},{"id":"2303.06808","title":"Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2305.09438","title":"MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2310.16937","title":"Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2402.03396","title":"UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2412.16594","title":"AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection","created":"2024-12-21","cited_by_count":5,"area":null},{"id":"2412.17754","title":"ADC: Enhancing Function Calling Via Adversarial Datasets and Code Line-Level Feedback","created":"2024-12-23","cited_by_count":5,"area":"agents"},{"id":"2502.20408","title":"Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2504.10557","title":"The Code Barrier: What LLMs Actually Understand?","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2205.01293","title":"A Survey of Deep Learning Models for Structural Code Understanding","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2208.07461","title":"A Library for Representing Python Programs as Graphs for Machine Learning","created":"2022-08-15","cited_by_count":4,"area":null},{"id":"2210.03003","title":"MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation","created":"2022-10-06","cited_by_count":4,"area":null},{"id":"2310.16253","title":"ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2406.11935","title":"A Problem-Oriented Perspective and Anchor Verification for Code Optimization","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2501.18916","title":"LLM Program Optimization via Retrieval Augmented Search","created":"2025-01-31","cited_by_count":4,"area":"rag"},{"id":"2504.07433","title":"From Token to Line: Enhancing Code Generation with a Long-Term Perspective","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2505.15039","title":"LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.20642","title":"CoderAgent: Simulating Student Behavior for Personalized Programming Learning with Large Language Models","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2511.00592","title":"Agentic Auto-Scheduling: An Experimental Study of LLM-Guided Loop Optimization","created":"2025-11-01","cited_by_count":4,"area":"agents"},{"id":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2207.07706","title":"Probing Semantic Grounding in Language Models of Code with Representational Similarity Analysis","created":"2022-07-15","cited_by_count":3,"area":null}],"next_cursor":"100"}