{"total":98,"rows":[{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631,"area":null},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300,"area":null},{"id":"2307.08177","title":"Using an LLM to Help With Code Understanding","created":"2023-07-17","cited_by_count":228,"area":null},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152,"area":null},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136,"area":null},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91,"area":null},{"id":"2303.16749","title":"Improving Code Generation by Training with Natural Language Feedback","created":"2023-03-28","cited_by_count":76,"area":null},{"id":"2303.17125","title":"A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges","created":"2023-03-30","cited_by_count":75,"area":null},{"id":"2406.16218","title":"Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs","created":"2024-06-23","cited_by_count":69,"area":null},{"id":"2305.00418","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","created":"2023-04-30","cited_by_count":53,"area":null},{"id":"2208.05950","title":"Interactive Code Generation via Test-Driven User-Intent Formalization","created":"2022-08-11","cited_by_count":50,"area":null},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2308.09895","title":"Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs","created":"2023-08-19","cited_by_count":45,"area":null},{"id":"2406.07765","title":"Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward","created":"2024-06-11","cited_by_count":45,"area":null},{"id":"2208.06213","title":"What is it like to program with artificial intelligence?","created":"2022-08-12","cited_by_count":39,"area":null},{"id":"2311.00889","title":"SALLM: Security Assessment of Generated Code","created":"2023-11-01","cited_by_count":39,"area":null},{"id":"2402.16197","title":"Language Models for Code Completion: A Practical Evaluation","created":"2024-02-25","cited_by_count":39,"area":null},{"id":"2306.04556","title":"StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2601.18341","title":"Agentic Much? Adoption of Coding Agents on GitHub","created":"2026-01-26","cited_by_count":32,"area":"agents"},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"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":"2306.04930","title":"When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming","created":"2023-06-08","cited_by_count":25,"area":"alignment"},{"id":"2406.00215","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","created":"2024-05-31","cited_by_count":24,"area":"agents"},{"id":"2511.04427","title":"Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects","created":"2025-11-06","cited_by_count":24,"area":"agents"},{"id":"2305.12050","title":"AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation","created":"2023-05-20","cited_by_count":21,"area":null},{"id":"2302.07248","title":"Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions","created":"2023-02-14","cited_by_count":20,"area":null},{"id":"2306.05153","title":"Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming","created":"2023-06-08","cited_by_count":20,"area":null},{"id":"2307.03817","title":"Exploring and Characterizing Large Language Models For Embedded System Development and Debugging","created":"2023-07-07","cited_by_count":20,"area":null},{"id":"2409.12447","title":"Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts","created":"2024-09-19","cited_by_count":19,"area":null},{"id":"2409.12699","title":"PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs)","created":"2024-09-19","cited_by_count":19,"area":null},{"id":"2508.04295","title":"EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation","created":"2025-08-06","cited_by_count":19,"area":null},{"id":"2406.17910","title":"Transforming Software Development: Evaluating the Efficiency and Challenges of GitHub Copilot in Real-World Projects","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2602.09185","title":"AIDev: Studying AI Coding Agents on GitHub","created":"2026-02-09","cited_by_count":17,"area":"agents"},{"id":"2507.07024","title":"FlexOlmo: Open Language Models for Flexible Data Use","created":"2025-07-09","cited_by_count":15,"area":"moe"},{"id":"2210.16494","title":"Aligning Offline Metrics and Human Judgments of Value for Code Generation Models","created":"2022-10-29","cited_by_count":14,"area":null},{"id":"2306.03203","title":"A Static Evaluation of Code Completion by Large Language Models","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2307.08220","title":"FRANC: A Lightweight Framework for High-Quality Code Generation","created":"2023-07-17","cited_by_count":14,"area":null},{"id":"2209.05948","title":"Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems","created":"2022-09-13","cited_by_count":13,"area":null},{"id":"2402.05650","title":"Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2402.15100","title":"Studying LLM Performance on Closed- and Open-source Data","created":"2024-02-23","cited_by_count":11,"area":null},{"id":"2601.13597","title":"AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development","created":"2026-01-20","cited_by_count":11,"area":"agents"},{"id":"2302.05678","title":"CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models","created":"2023-02-11","cited_by_count":10,"area":null},{"id":"2401.09964","title":"When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference","created":"2024-01-18","cited_by_count":10,"area":null},{"id":"2404.10155","title":"The Fault in our Stars: Quality Assessment of Code Generation Benchmarks","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2602.06593","title":"AgentStepper: Interactive Debugging of Software Development Agents","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2503.16491","title":"The Impact of Generative AI Coding Assistants on Developers Who Are Visually Impaired","created":"2025-03-10","cited_by_count":7,"area":null},{"id":"2405.15512","title":"ChatGPT Code Detection: Techniques for Uncovering the Source of Code","created":"2024-05-24","cited_by_count":6,"area":null},{"id":"2412.09058","title":"EmbedGenius: Towards Automated Software Development for Generic Embedded IoT Systems","created":"2024-12-12","cited_by_count":6,"area":null},{"id":"2601.18345","title":"Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2308.13507","title":"Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Code","created":"2023-08-25","cited_by_count":5,"area":null},{"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":"2408.01050","title":"The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2503.06195","title":"Human-AI Experience in Integrated Development Environments: A Systematic Literature Review","created":"2025-03-08","cited_by_count":5,"area":null},{"id":"2604.00917","title":"Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time","created":"2026-04-01","cited_by_count":5,"area":"agents"},{"id":"2604.03551","title":"AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub","created":"2026-04-04","cited_by_count":5,"area":"agents"},{"id":"2305.14874","title":"From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2405.08704","title":"Full Line Code Completion: Bringing AI to Desktop","created":"2024-05-14","cited_by_count":4,"area":null},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2501.02628","title":"Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets","created":"2025-01-05","cited_by_count":4,"area":null},{"id":"2507.03156","title":"The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2508.07966","title":"Exploring the Challenges and Opportunities of AI-assisted Codebase Generation","created":"2025-08-11","cited_by_count":4,"area":null},{"id":"2508.12285","title":"\"My productivity is boosted, but ...\" Demystifying Users' Perception on AI Coding Assistants","created":"2025-08-17","cited_by_count":4,"area":null},{"id":"2603.05744","title":"CodeScout: Contextual Problem Statement Enhancement for Software Agents","created":"2026-03-05","cited_by_count":4,"area":"agents"},{"id":"2402.12222","title":"CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2404.02933","title":"NL2KQL: From Natural Language to Kusto Query","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2602.08915","title":"Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance","created":"2026-02-09","cited_by_count":3,"area":"agents"},{"id":"2606.13175","title":"The End of Code Review: Coding Agents Supersede Human Inspection","created":"2026-06-11","cited_by_count":3,"area":"agents"},{"id":"2505.15469","title":"A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2603.16975","title":"The State of Generative AI in Software Development: Insights from Literature and a Developer Survey","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2502.13199","title":"The Role of GitHub Copilot on Software Development: A Perspective on Productivity, Security, Best Practices and Future Directions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2504.20196","title":"Understanding and supporting how developers prompt for LLM-powered code editing in practice","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2510.25662","title":"User Misconceptions of LLM-Based Conversational Programming Assistants","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.02197","title":"Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs","created":"2025-11-04","cited_by_count":1,"area":"lr"},{"id":"2604.09388","title":"The AI Codebase Maturity Model: From Assisted Coding to Fully Autonomous Systems","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2607.01418","title":"Adoption and Impact of Command-Line AI Coding Agents: A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.03174","title":"Effectiveness of LLM-based Software Diversity for Reliability Improvement -- an Empirical Study","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2402.17442","title":"Insights from the Usage of the Ansible Lightspeed Code Completion Service","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2412.15441","title":"Insights into resource utilization of code small language models serving with runtime engines and execution providers","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2503.16144","title":"Unify and Triumph: Polyglot, Diverse, and Self-Consistent Generation of Unit Tests with LLMs","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2510.11516","title":"Cracking CodeWhisperer: Analyzing Developers' Interactions and Patterns During Programming Tasks","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2512.18261","title":"Software Vulnerability Management in the Era of Artificial Intelligence: An Industry Perspective","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.22935","title":"Protecting Private Code in IDE Autocomplete using Differential Privacy","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.01849","title":"From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.18284","title":"CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2606.04273","title":"Human agency in initial human-AI proof formalization workflows","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.01810","title":"Decoupling Code Complexity from Newcomer Participation: A Causal Study of AI Coding Agent Adoption in OSS","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.08691","title":"ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.09902","title":"Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.11348","title":"Understanding the Impact of AI Code Assistants on Security API Usage: An Empirical Study","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.22898","title":"AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.06069","title":"Training-Free Token-Level Steering for LLM Personalized Co-Writing","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.20903","title":"Generation of Web Apps with Agentic IDEs: An Empirical Assessment","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.30756","title":"On the Prospects of Dynamic LLM Conversations in Software Development","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.12708","title":"What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.15794","title":"KnowBench: Effort Reduction as a Unified, Deployment-Grounded Benchmark for Clinical AI","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.12849","title":"Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}