{"list":"other","total":97,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171},{"id":"2310.02304","title":"Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation","created":"2023-10-03","cited_by_count":148},{"id":"2505.16400","title":"AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning","created":"2025-05-22","cited_by_count":87},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62},{"id":"2108.11590","title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","created":"2021-08-26","cited_by_count":59},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57},{"id":"2301.03270","title":"A Survey of Learning-based Automated Program Repair","created":"2023-01-09","cited_by_count":55},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53},{"id":"2410.00752","title":"TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark","created":"2024-10-01","cited_by_count":52},{"id":"2503.15223","title":"Are \"Solved Issues\" in SWE-bench Really Solved Correctly? An Empirical Study","created":"2025-03-19","cited_by_count":49},{"id":"2312.12450","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","created":"2023-12-11","cited_by_count":48},{"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},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46},{"id":"2406.07436","title":"McEval: Massively Multilingual Code Evaluation","created":"2024-06-11","cited_by_count":44},{"id":"2406.04531","title":"TESTEVAL: Benchmarking Large Language Models for Test Case Generation","created":"2024-06-06","cited_by_count":40},{"id":"2311.08588","title":"CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation","created":"2023-11-14","cited_by_count":39},{"id":"2505.07897","title":"LongCodeBench: Evaluating Coding LLMs at 1M Context Windows","created":"2025-05-12","cited_by_count":37},{"id":"2412.06176","title":"AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement","created":"2024-12-09","cited_by_count":35},{"id":"2402.13521","title":"Test-Driven Development for Code Generation","created":"2024-02-21","cited_by_count":34},{"id":"2502.18658","title":"Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support","created":"2025-02-25","cited_by_count":34},{"id":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30},{"id":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30},{"id":"2503.07701","title":"Automated Benchmark Generation for Repository-Level Coding Tasks","created":"2025-03-10","cited_by_count":29},{"id":"2505.13938","title":"CLEVER: A Curated Benchmark for Formally Verified Code Generation","created":"2025-05-20","cited_by_count":29},{"id":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28},{"id":"2406.06918","title":"HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation","created":"2024-06-11","cited_by_count":28},{"id":"2410.24117","title":"AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation","created":"2024-10-31","cited_by_count":28},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27},{"id":"2403.04814","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks","created":"2024-03-07","cited_by_count":25},{"id":"2506.03011","title":"Coding Agents with Multimodal Browsing are Generalist Problem Solvers","created":"2025-06-03","cited_by_count":25},{"id":"2505.04606","title":"OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution","created":"2025-05-07","cited_by_count":24},{"id":"2507.05269","title":"CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","created":"2025-07-03","cited_by_count":24},{"id":"2308.08961","title":"On the Evaluation of Neural Code Translation: Taxonomy and Benchmark","created":"2023-08-17","cited_by_count":23},{"id":"2412.17744","title":"RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation","created":"2024-12-23","cited_by_count":23},{"id":"2503.04149","title":"Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination","created":"2025-03-06","cited_by_count":23},{"id":"2402.10754","title":"LLMDFA: Analyzing Dataflow in Code with Large Language Models","created":"2024-02-16","cited_by_count":22},{"id":"2402.12317","title":"EVOR: Evolving Retrieval for Code Generation","created":"2024-02-19","cited_by_count":22},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21},{"id":"2504.15254","title":"CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation","created":"2025-04-21","cited_by_count":19},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18},{"id":"2507.19060","title":"PurpCode: Reasoning for Safer Code Generation","created":"2025-07-25","cited_by_count":18},{"id":"2410.09812","title":"Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?","created":"2024-10-13","cited_by_count":17},{"id":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16},{"id":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14},{"id":"2507.06920","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","created":"2025-07-09","cited_by_count":14},{"id":"2404.12636","title":"MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning","created":"2024-04-19","cited_by_count":13},{"id":"2403.00448","title":"When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done?","created":"2024-03-01","cited_by_count":12},{"id":"2505.18955","title":"Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models","created":"2025-05-25","cited_by_count":12},{"id":"2505.22704","title":"Training Language Models to Generate Quality Code with Program Analysis Feedback","created":"2025-05-28","cited_by_count":12},{"id":"2501.11709","title":"Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution","created":"2025-01-20","cited_by_count":11},{"id":"2506.00419","title":"Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences","created":"2025-05-31","cited_by_count":10},{"id":"2506.10948","title":"Execution Guided Line-by-Line Code Generation","created":"2025-06-12","cited_by_count":10},{"id":"2403.16354","title":"ChatDBG: Augmenting Debugging with Large Language Models","created":"2024-03-25","cited_by_count":9},{"id":"2412.17315","title":"CodeV: Issue Resolving with Visual Data","created":"2024-12-23","cited_by_count":9},{"id":"2504.14640","title":"Risk Assessment Framework for Code LLMs via Leveraging Internal States","created":"2025-04-20","cited_by_count":9},{"id":"2408.12056","title":"Enhancing Automated Program Repair with Solution Design","created":"2024-08-22","cited_by_count":8},{"id":"2407.17631","title":"BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning","created":"2024-07-24","cited_by_count":7},{"id":"2411.06774","title":"The First Prompt Counts the Most! An Evaluation of Large Language Models on Iterative Example-Based Code Generation","created":"2024-11-11","cited_by_count":7},{"id":"2501.13699","title":"DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale","created":"2025-01-23","cited_by_count":7},{"id":"2503.20576","title":"Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models","created":"2025-03-26","cited_by_count":7},{"id":"2505.20625","title":"Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration","created":"2025-05-27","cited_by_count":7},{"id":"2508.07434","title":"Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs","created":"2025-08-10","cited_by_count":7},{"id":"2310.13229","title":"The GitHub Recent Bugs Dataset for Evaluating LLM-based Debugging Applications","created":"2023-10-20","cited_by_count":6},{"id":"2408.03680","title":"Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs","created":"2024-08-07","cited_by_count":6},{"id":"2412.16589","title":"Improving FIM Code Completions via Context & Curriculum Based Learning","created":"2024-12-21","cited_by_count":6},{"id":"2509.01616","title":"Automated Generation of Issue-Reproducing Tests by Combining LLMs and Search-Based Testing","created":"2025-09-01","cited_by_count":5},{"id":"2509.04078","title":"RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models","created":"2025-09-04","cited_by_count":5},{"id":"2410.07793","title":"Do Current Language Models Support Code Intelligence for R Programming Language?","created":"2024-10-10","cited_by_count":4},{"id":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4},{"id":"2504.02141","title":"On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software","created":"2025-04-02","cited_by_count":3},{"id":"2505.23471","title":"Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency","created":"2025-05-29","cited_by_count":3},{"id":"2506.10525","title":"AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT Length","created":"2025-06-12","cited_by_count":3},{"id":"2509.11686","title":"Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models","created":"2025-09-15","cited_by_count":3},{"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},{"id":"2506.11153","title":"QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation","created":"2025-06-11","cited_by_count":2},{"id":"2509.23686","title":"Evaluating Program Semantics Reasoning with Type Inference in System F","created":"2025-09-28","cited_by_count":2},{"id":"2507.13555","title":"Demystifying Feature Requests: Leveraging LLMs to Refine Feature Requests in Open-Source Software","created":"2025-07-17","cited_by_count":1}],"next_cursor":null}