{"list":"other","total":100,"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":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"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":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2504.21776","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","created":"2025-04-30","cited_by_count":335},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"id":"2404.04834","title":"LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead","created":"2024-04-07","cited_by_count":155},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"2305.02309","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","created":"2023-05-03","cited_by_count":125},{"id":"2303.07263","title":"InferFix: End-to-End Program Repair with LLMs","created":"2023-03-13","cited_by_count":114},{"id":"2412.19048","title":"Jasper and Stella: distillation of SOTA embedding models","created":"2024-12-26","cited_by_count":112},{"id":"2206.12839","title":"Repository-Level Prompt Generation for Large Language Models of Code","created":"2022-06-26","cited_by_count":106},{"id":"2508.00083","title":"A Survey on Code Generation with LLM-based Agents","created":"2025-07-31","cited_by_count":106},{"id":"2311.16543","title":"RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models","created":"2023-11-28","cited_by_count":100},{"id":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91},{"id":"2501.05040","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","created":"2025-01-09","cited_by_count":90},{"id":"2503.09089","title":"LocAgent: Graph-Guided LLM Agents for Code Localization","created":"2025-03-12","cited_by_count":86},{"id":"2402.09171","title":"Automated Unit Test Improvement using Large Language Models at Meta","created":"2024-02-14","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":"2212.10007","title":"CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context","created":"2022-12-20","cited_by_count":65},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58},{"id":"2507.23348","title":"SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution","created":"2025-07-31","cited_by_count":53},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50},{"id":"2403.16792","title":"Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback","created":"2024-03-25","cited_by_count":46},{"id":"2502.00350","title":"OrcaLoca: An LLM Agent Framework for Software Issue Localization","created":"2025-02-01","cited_by_count":45},{"id":"2407.19487","title":"RLCoder: Reinforcement Learning for Repository-Level Code Completion","created":"2024-07-28","cited_by_count":44},{"id":"2505.15155","title":"R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization","created":"2025-05-21","cited_by_count":43},{"id":"2306.10998","title":"RepoFusion: Training Code Models to Understand Your Repository","created":"2023-06-19","cited_by_count":40},{"id":"2405.19782","title":"Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion","created":"2024-05-30","cited_by_count":40},{"id":"2410.22821","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","created":"2024-10-30","cited_by_count":34},{"id":"2411.12644","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval","created":"2024-11-19","cited_by_count":34},{"id":"2402.14323","title":"REPOFUSE: Repository-Level Code Completion with Fused Dual Context","created":"2024-02-22","cited_by_count":32},{"id":"2401.06391","title":"Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation","created":"2024-01-12","cited_by_count":30},{"id":"2502.20127","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","created":"2025-02-27","cited_by_count":28},{"id":"2503.21710","title":"Enhancing repository-level software repair via repository-aware knowledge graphs","created":"2025-03-27","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":"2406.10018","title":"STALL+: Boosting LLM-based Repository-level Code Completion with Static Analysis","created":"2024-06-14","cited_by_count":21},{"id":"2505.01976","title":"A Survey on Privacy Risks and Protection in Large Language Models","created":"2025-05-04","cited_by_count":21},{"id":"2308.09313","title":"Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases","created":"2023-08-18","cited_by_count":19},{"id":"2505.21577","title":"RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving","created":"2025-05-27","cited_by_count":19},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19},{"id":"2401.04514","title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search","created":"2024-01-09","cited_by_count":17},{"id":"2504.16429","title":"Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection","created":"2025-04-23","cited_by_count":16},{"id":"2401.01701","title":"De-Hallucinator: Mitigating LLM Hallucinations in Code Generation Tasks via Iterative Grounding","created":"2024-01-03","cited_by_count":15},{"id":"2403.06095","title":"RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion","created":"2024-03-10","cited_by_count":15},{"id":"2508.03012","title":"Tool-integrated Reinforcement Learning for Repo Deep Search","created":"2025-08-05","cited_by_count":15},{"id":"2405.01573","title":"Class-Level Code Generation from Natural Language Using Iterative, Tool-Enhanced Reasoning over Repository","created":"2024-04-22","cited_by_count":14},{"id":"2406.18294","title":"Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs","created":"2024-06-26","cited_by_count":13},{"id":"2307.15370","title":"Private-Library-Oriented Code Generation with Large Language Models","created":"2023-07-28","cited_by_count":10},{"id":"2402.03630","title":"Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context","created":"2024-02-06","cited_by_count":10},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10},{"id":"2406.01359","title":"R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models","created":"2024-06-03","cited_by_count":9},{"id":"2409.00921","title":"Statically Contextualizing Large Language Models with Typed Holes","created":"2024-09-02","cited_by_count":9},{"id":"2505.08120","title":"Putting It All into Context: Simplifying Agents with LCLMs","created":"2025-05-12","cited_by_count":9},{"id":"2503.15301","title":"aiXcoder-7B-v2: Training LLMs to Fully Utilize the Long Context in Repository-level Code Completion","created":"2025-03-19","cited_by_count":8},{"id":"2507.13369","title":"VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation","created":"2025-07-09","cited_by_count":8},{"id":"2509.25257","title":"RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval","created":"2025-09-27","cited_by_count":7},{"id":"2410.13542","title":"LLM-based Unit Test Generation via Property Retrieval","created":"2024-10-17","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":"2502.09771","title":"Knowledge-Enhanced Program Repair for Data Science Code","created":"2025-02-13","cited_by_count":6},{"id":"2507.20888","title":"Enhancing Project-Specific Code Completion by Inferring Internal API Information","created":"2025-07-28","cited_by_count":5},{"id":"2509.07941","title":"ImportSnare: Directed \"Code Manual\" Hijacking in Retrieval-Augmented Code Generation","created":"2025-09-09","cited_by_count":5},{"id":"2410.18251","title":"Context-Augmented Code Generation Using Programming Knowledge Graphs","created":"2024-10-09","cited_by_count":4},{"id":"2504.08975","title":"Code-Craft: Hierarchical Graph-Based Code Summarization for Enhanced Context Retrieval","created":"2025-04-11","cited_by_count":4},{"id":"2505.14394","title":"Knowledge Graph Based Repository-Level Code Generation","created":"2025-05-20","cited_by_count":4},{"id":"2509.05980","title":"GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion","created":"2025-09-07","cited_by_count":4},{"id":"2412.08063","title":"ContextModule: Improving Code Completion via Repository-level Contextual Information","created":"2024-12-11","cited_by_count":3},{"id":"2508.05224","title":"Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning","created":"2025-08-07","cited_by_count":3},{"id":"2509.21427","title":"Extracting Conceptual Knowledge to Locate Software Issues","created":"2025-09-25","cited_by_count":3},{"id":"2502.17139","title":"FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verification","created":"2025-02-24","cited_by_count":2},{"id":"2503.23231","title":"CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models","created":"2025-03-29","cited_by_count":2},{"id":"2504.07740","title":"Zero-Shot Cross-Domain Code Search without Fine-Tuning","created":"2025-04-10","cited_by_count":2},{"id":"2412.03815","title":"Synergizing LLMs and Knowledge Graphs: A Novel Approach to Software Repository-Related Question Answering","created":"2024-12-05","cited_by_count":1},{"id":"2508.09537","title":"From Context to Intent: Reasoning-Guided Function-Level Code Completion","created":"2025-08-13","cited_by_count":1}],"next_cursor":null}