{"total":72,"rows":[{"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":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"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":"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,"area":null},{"id":"2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","created":"2025-03-31","cited_by_count":43,"area":"agents"},{"id":"2507.17773","title":"MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation","created":"2025-07-20","cited_by_count":38,"area":null},{"id":"2410.22821","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","created":"2024-10-30","cited_by_count":34,"area":null},{"id":"2501.07811","title":"CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation","created":"2025-01-14","cited_by_count":34,"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":"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":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2408.13204","title":"DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation","created":"2024-08-23","cited_by_count":21,"area":null},{"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":"2504.15254","title":"CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation","created":"2025-04-21","cited_by_count":19,"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":"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":"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":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"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":"2503.22688","title":"CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation","created":"2025-03-05","cited_by_count":15,"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":"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":"2604.19572","title":"A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression","created":"2026-04-21","cited_by_count":15,"area":"inference"},{"id":"2502.10802","title":"CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2602.01655","title":"ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development","created":"2026-02-02","cited_by_count":12,"area":"agents"},{"id":"2602.21611","title":"Structurally Aligned Subtask-Level Memory for Software Engineering Agents","created":"2026-02-25","cited_by_count":12,"area":"agents"},{"id":"2406.12902","title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","created":"2024-06-10","cited_by_count":10,"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":"2605.24110","title":"EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions","created":"2026-05-22","cited_by_count":9,"area":"agents"},{"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":"2511.03404","title":"Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling","created":"2025-11-05","cited_by_count":6,"area":"agents"},{"id":"2605.20563","title":"Multi-agent Collaboration with State Management","created":"2026-05-19","cited_by_count":6,"area":"agents"},{"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":"2509.13758","title":"A Study on Thinking Patterns of Large Reasoning Models in Code Generation","created":"2025-09-17","cited_by_count":5,"area":"lr"},{"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":"2606.00953","title":"When Parallelism Pays Off: Cohesion-Aware Task Partitioning for Multi-Agent Coding","created":"2026-05-31","cited_by_count":5,"area":"agents"},{"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":"2410.06949","title":"Towards Exception Safety Code Generation with Intermediate Representation Agents Framework","created":"2024-10-09","cited_by_count":3,"area":"agents"},{"id":"2502.19149","title":"Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval","created":"2025-02-26","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":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2412.11713","title":"Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework","created":"2024-12-16","cited_by_count":2,"area":"agents"},{"id":"2502.17139","title":"FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verification","created":"2025-02-24","cited_by_count":2,"area":"inference"},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2604.26923","title":"ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation","created":"2026-04-29","cited_by_count":2,"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":"2604.03632","title":"Persistent Cross-Attempt State Optimization for Repository-Level Code Generation","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2604.19750","title":"Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2605.05700","title":"An Empirical Study of Proactive Coding Assistants in Real-World Software Development","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.14563","title":"Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2605.26186","title":"SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2606.13763","title":"Do programming languages still matter to your AI coding agent teammate? Evidence at scale from chess engines","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2608.01927","title":"Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation","created":"2026-08-03","cited_by_count":1,"area":"rag"},{"id":"2609.37143","title":"LoLBench: Evaluating Coding Agents with Long-Horizon Proposals on Large Software Systems","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2508.20119","title":"LLM Agents for Generating Microservice-based Applications: how complex is your specification?","created":"2025-08-22","cited_by_count":0,"area":"agents"},{"id":"2510.27565","title":"CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments","created":"2025-10-31","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":"2604.03622","title":"Toward Executable Repository-Level Code Generation via Environment Alignment","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.11514","title":"DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2607.07619","title":"Rethinking Code Performance Benchmarks for LLMs","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2607.08691","title":"ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.21208","title":"Specification Portability Across LLM Development Agents: Cross-Agent Compatibility in Specification-Driven Software Migration","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.14992","title":"MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.26480","title":"FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.37233","title":"DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38335","title":"E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}