{"total":37,"rows":[{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"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":"2412.14234","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","created":"2024-12-18","cited_by_count":16,"area":null},{"id":"2412.14764","title":"CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2410.08806","title":"Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs","created":"2024-10-11","cited_by_count":8,"area":null},{"id":"2512.22154","title":"Practical challenges of control monitoring in frontier AI deployments","created":"2025-12-15","cited_by_count":8,"area":null},{"id":"2409.19894","title":"TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2508.01443","title":"Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective","created":"2025-08-02","cited_by_count":7,"area":null},{"id":"2501.11086","title":"Evaluating LLM-Based Regression Test Generation","created":"2025-01-19","cited_by_count":6,"area":null},{"id":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2604.06742","title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2504.20781","title":"Using LLMs in Generating Design Rationale for Software Architecture Decisions","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2509.16187","title":"MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2411.00006","title":"Personality-Guided Code Generation Using Large Language Models","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2606.08049","title":"SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2511.12033","title":"EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation","created":"2025-11-15","cited_by_count":2,"area":null},{"id":"2608.09277","title":"P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2504.00521","title":"Automated detection of atomicity violations in large-scale systems","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.05106","title":"SpeakEasy: Enhancing Text-to-Speech Interactions for Expressive Content Creation","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2512.01396","title":"BackportBench: A Multilingual Benchmark for Automated Backporting of Patches","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2605.18073","title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.09800","title":"FASE: Fast Adaptive Semantic Entropy for Code Quality","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2510.01453","title":"The Command Line GUIde: Graphical Interfaces from Man Pages via AI","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2601.22345","title":"Failing to Explore: Language Models on Interactive Tasks","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2605.13138","title":"A Comprehensive Evaluation of Code Language Models for Security Patch Detection","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.30208","title":"Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.24834","title":"Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2609.34378","title":"Marathoner: Ultra-Long-Horizon Autonomous Intelligence","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}