{"total":119,"rows":[{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203,"area":"lr"},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2306.15626","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","created":"2023-06-27","cited_by_count":427,"area":"rag"},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367,"area":null},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274,"area":"agents"},{"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":"2406.13629","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","created":"2024-06-19","cited_by_count":101,"area":"rag"},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98,"area":"rag"},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2403.05313","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","created":"2024-03-08","cited_by_count":75,"area":"lr"},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69,"area":null},{"id":"2406.11147","title":"Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG","created":"2024-06-17","cited_by_count":68,"area":null},{"id":"2410.07590","title":"TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text","created":"2024-10-10","cited_by_count":63,"area":"rag"},{"id":"2403.10059","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","created":"2024-03-15","cited_by_count":55,"area":"rag"},{"id":"2210.17236","title":"When Language Model Meets Private Library","created":"2022-10-31","cited_by_count":54,"area":null},{"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,"area":null},{"id":"2309.06057","title":"RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair","created":"2023-09-12","cited_by_count":44,"area":"rag"},{"id":"2306.10998","title":"RepoFusion: Training Code Models to Understand Your Repository","created":"2023-06-19","cited_by_count":40,"area":null},{"id":"2405.19782","title":"Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion","created":"2024-05-30","cited_by_count":40,"area":null},{"id":"2406.06822","title":"An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection","created":"2024-06-10","cited_by_count":40,"area":"safety"},{"id":"2406.07003","title":"GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model","created":"2024-06-11","cited_by_count":40,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2410.06209","title":"LeanAgent: Lifelong Learning for Formal Theorem Proving","created":"2024-10-08","cited_by_count":35,"area":"lr"},{"id":"2402.14323","title":"REPOFUSE: Repository-Level Code Completion with Fused Dual Context","created":"2024-02-22","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":"2308.10462","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","created":"2023-08-21","cited_by_count":28,"area":null},{"id":"2303.17780","title":"AceCoder: Utilizing Existing Code to Enhance Code Generation","created":"2023-03-31","cited_by_count":25,"area":null},{"id":"2510.04905","title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","created":"2025-10-06","cited_by_count":23,"area":"rag"},{"id":"2212.04634","title":"Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey","created":"2022-12-09","cited_by_count":22,"area":null},{"id":"2311.02775","title":"AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs","created":"2023-11-05","cited_by_count":22,"area":"alignment"},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2503.20589","title":"What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond","created":"2025-03-26","cited_by_count":22,"area":"rag"},{"id":"2410.04194","title":"Consistent Autoformalization for Constructing Mathematical Libraries","created":"2024-10-05","cited_by_count":21,"area":null},{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"area":null},{"id":"2206.11719","title":"AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models","created":"2022-06-23","cited_by_count":16,"area":null},{"id":"2405.07530","title":"Prompt-based Code Completion via Multi-Retrieval Augmented Generation","created":"2024-05-13","cited_by_count":16,"area":"rag"},{"id":"2310.16263","title":"Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation","created":"2023-10-25","cited_by_count":15,"area":null},{"id":"2306.00381","title":"Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2601.07348","title":"Controlled Self-Evolution for Algorithmic Code Optimization","created":"2026-01-12","cited_by_count":12,"area":null},{"id":"2404.14296","title":"Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach","created":"2024-04-22","cited_by_count":11,"area":"safety"},{"id":"2406.11925","title":"DocCGen: Document-based Controlled Code Generation","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2502.18139","title":"LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers","created":"2025-02-25","cited_by_count":11,"area":"rag"},{"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,"area":null},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2404.01554","title":"FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completion","created":"2024-04-02","cited_by_count":9,"area":"rag"},{"id":"2409.00921","title":"Statically Contextualizing Large Language Models with Typed Holes","created":"2024-09-02","cited_by_count":9,"area":null},{"id":"2406.03283","title":"CATCODER: Repository-Level Code Generation with Relevant Code and Type Context","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2508.14066","title":"Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation","created":"2025-08-11","cited_by_count":8,"area":"rag"},{"id":"2411.19463","title":"Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems","created":"2024-11-29","cited_by_count":7,"area":"rag"},{"id":"2507.23096","title":"ChatVis: Large Language Model Agent for Generating Scientific Visualizations","created":"2025-07-30","cited_by_count":7,"area":"agents"},{"id":"2510.18204","title":"RESCUE: Retrieval Augmented Secure Code Generation","created":"2025-10-21","cited_by_count":7,"area":"rag"},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2212.10692","title":"Generation-Augmented Query Expansion For Code Retrieval","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2411.05199","title":"CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2506.04565","title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2506.11591","title":"Retrieval-Augmented Code Review Comment Generation","created":"2025-06-13","cited_by_count":6,"area":"rag"},{"id":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2601.18847","title":"MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution","created":"2026-01-26","cited_by_count":6,"area":"rag"},{"id":"2603.27277","title":"Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP","created":"2026-03-28","cited_by_count":6,"area":"agents"},{"id":"2405.14753","title":"A Transformer-Based Approach for Smart Invocation of Automatic Code Completion","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2410.16229","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","created":"2024-10-21","cited_by_count":5,"area":"rag"},{"id":"2505.06302","title":"QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives","created":"2025-05-08","cited_by_count":5,"area":null},{"id":"2505.15179","title":"RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry","created":"2025-05-21","cited_by_count":5,"area":"rag"},{"id":"2507.18515","title":"A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat","created":"2025-07-24","cited_by_count":5,"area":"rag"},{"id":"2507.20888","title":"Enhancing Project-Specific Code Completion by Inferring Internal API Information","created":"2025-07-28","cited_by_count":5,"area":null},{"id":"2508.05970","title":"Impact-driven Context Filtering For Cross-file Code Completion","created":"2025-08-08","cited_by_count":5,"area":"rag"},{"id":"2312.09126","title":"Towards Trustworthy AI Software Development Assistance","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2405.02355","title":"CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation","created":"2024-05-03","cited_by_count":4,"area":"rag"},{"id":"2407.04794","title":"On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks","created":"2024-07-05","cited_by_count":4,"area":"safety"},{"id":"2407.20207","title":"QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2410.03234","title":"Showing LLM-Generated Code Selectively Based on Confidence of LLMs","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2506.05766","title":"BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2506.16444","title":"REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2506.20081","title":"SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization","created":"2025-06-25","cited_by_count":4,"area":"rag"},{"id":"2205.10674","title":"NS3: Neuro-Symbolic Semantic Code Search","created":"2022-05-21","cited_by_count":3,"area":null},{"id":"2209.06634","title":"Automatic Comment Generation via Multi-Pass Deliberation","created":"2022-09-14","cited_by_count":3,"area":null},{"id":"2403.09740","title":"Teaching Machines to Code: Smart Contract Translation with LLMs","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2502.17441","title":"Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projects","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2506.03535","title":"Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generation","created":"2025-06-04","cited_by_count":3,"area":"rag"},{"id":"2510.20609","title":"Practical Code RAG at Scale: Task-Aware Retrieval Design Choices under Compute Budgets","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2212.09132","title":"JEMMA: An Extensible Java Dataset for ML4Code Applications","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2309.00584","title":"Laminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2409.15228","title":"A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2412.12447","title":"PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation","created":"2024-12-17","cited_by_count":2,"area":"rag"},{"id":"2503.08161","title":"OASIS: Order-Augmented Strategy for Improved Code Search","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.12483","title":"MoT: Modularization-of-Thought Prompting for Effective Code Generation","created":"2025-03-16","cited_by_count":2,"area":"lr"},{"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,"area":null},{"id":"2504.15080","title":"Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2504.21043","title":"CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2507.19033","title":"SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation","created":"2025-07-25","cited_by_count":2,"area":"rag"},{"id":"2508.02473","title":"NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2511.05302","title":"When More Retrieval Hurts: Retrieval-Augmented Code Review Generation","created":"2025-11-07","cited_by_count":2,"area":"rag"},{"id":"2602.02029","title":"Canonical Intermediate Representation for LLM-based optimization problem formulation and code generation","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2608.16742","title":"TDD-Agent: Test-Driven Reasoning for Code Generation","created":"2026-08-17","cited_by_count":2,"area":"lr"},{"id":"2204.11594","title":"Addressing Leakage in Self-Supervised Contextualized Code Retrieval","created":"2022-04-17","cited_by_count":1,"area":null},{"id":"2309.12732","title":"OpenAi's GPT4 as coding assistant","created":"2023-09-22","cited_by_count":1,"area":null},{"id":"2312.08976","title":"Dynamic Retrieval-Augmented Generation","created":"2023-12-14","cited_by_count":1,"area":"rag"},{"id":"2406.03092","title":"FragRel: Exploiting Fragment-level Relations in the External Memory of Large Language Models","created":"2024-06-05","cited_by_count":1,"area":null}],"next_cursor":"100"}