{"total":72,"rows":[{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2503.06680","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","created":"2025-03-09","cited_by_count":58,"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":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2502.13681","title":"Repo2Run: Automated Building Executable Environment for Code Repository at Scale","created":"2025-02-19","cited_by_count":39,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35,"area":null},{"id":"2503.07010","title":"ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation","created":"2025-03-10","cited_by_count":26,"area":"agents"},{"id":"2506.07636","title":"SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling","created":"2025-06-09","cited_by_count":26,"area":"agents"},{"id":"2510.06186","title":"RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback","created":"2025-10-07","cited_by_count":25,"area":"alignment"},{"id":"2506.07966","title":"SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence","created":"2025-06-09","cited_by_count":23,"area":"mllm"},{"id":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2601.00376","title":"In Line with Context: Repository-Level Code Generation via Context Inlining","created":"2026-01-01","cited_by_count":18,"area":null},{"id":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17,"area":null},{"id":"2504.10046","title":"GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation","created":"2025-04-14","cited_by_count":17,"area":"rag"},{"id":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2506.04592","title":"Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification","created":"2025-06-05","cited_by_count":17,"area":"lr"},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15,"area":null},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2506.12915","title":"PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization","created":"2025-06-15","cited_by_count":15,"area":null},{"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":"2601.10343","title":"OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding","created":"2026-01-15","cited_by_count":15,"area":"agents"},{"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,"area":null},{"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":"2512.04111","title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","created":"2025-11-30","cited_by_count":12,"area":"agents"},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","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":"2601.20882","title":"DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","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":"2605.24110","title":"EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions","created":"2026-05-22","cited_by_count":9,"area":"agents"},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"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,"area":null},{"id":"2503.10452","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2509.22237","title":"FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2606.19830","title":"JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines","created":"2026-06-18","cited_by_count":6,"area":null},{"id":"2505.04406","title":"YABLoCo: Yet Another Benchmark for Long Context Code Generation","created":"2025-05-07","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":"2510.00415","title":"Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm","created":"2025-10-01","cited_by_count":5,"area":"agents"},{"id":"2510.04852","title":"FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration","created":"2025-10-06","cited_by_count":5,"area":"agents"},{"id":"2601.13240","title":"KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2412.01621","title":"NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers","created":"2024-12-02","cited_by_count":4,"area":"lr"},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2504.12608","title":"Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2505.14394","title":"Knowledge Graph Based Repository-Level Code Generation","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","cited_by_count":4,"area":"agents"},{"id":"2502.11167","title":"SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors","created":"2025-02-16","cited_by_count":3,"area":null},{"id":"2503.09217","title":"Evaluating the Generalizability of LLMs in Automated Program Repair","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2507.05281","title":"CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2510.22099","title":"Generalization or Memorization: Dynamic Decoding for Mode Steering","created":"2025-10-25","cited_by_count":3,"area":"mechinterp"},{"id":"2605.07024","title":"Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2603.15921","title":"VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2605.29277","title":"Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.20517","title":"Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2507.02912","title":"Deep Graph Learning for Industrial Carbon Emission Analysis and Policy Impact","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2508.09537","title":"From Context to Intent: Reasoning-Guided Function-Level Code Completion","created":"2025-08-13","cited_by_count":1,"area":"lr"},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2603.27745","title":"Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits","created":"2026-03-29","cited_by_count":1,"area":"agents"},{"id":"2505.21514","title":"SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2604.02709","title":"Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.04226","title":"SW-$A^2$-Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web","created":"2026-04-05","cited_by_count":0,"area":"agents"},{"id":"2607.08981","title":"The Patchwork Problem in LLM-Generated Code","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2610.18206","title":"SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}