{"total":85,"rows":[{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391,"area":null},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278,"area":null},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256,"area":null},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232,"area":"agents"},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2304.11938","title":"Is ChatGPT the Ultimate Programming Assistant -- How far is it?","created":"2023-04-24","cited_by_count":76,"area":null},{"id":"2304.06815","title":"Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)","created":"2023-04-13","cited_by_count":72,"area":null},{"id":"2409.00899","title":"MarsCode Agent: AI-native Automated Bug Fixing","created":"2024-09-02","cited_by_count":71,"area":"agents"},{"id":"2308.03314","title":"GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis","created":"2023-08-07","cited_by_count":65,"area":null},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"area":null},{"id":"2305.18607","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","created":"2023-05-29","cited_by_count":52,"area":null},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52,"area":null},{"id":"2312.15698","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","created":"2023-12-25","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":"2310.09748","title":"Large Language Model-Aware In-Context Learning for Code Generation","created":"2023-10-15","cited_by_count":43,"area":null},{"id":"2405.18649","title":"LeDex: Training LLMs to Better Self-Debug and Explain Code","created":"2024-05-28","cited_by_count":40,"area":null},{"id":"2412.21199","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","created":"2024-12-30","cited_by_count":39,"area":null},{"id":"2412.01778","title":"HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing","created":"2024-12-02","cited_by_count":37,"area":"agents"},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35,"area":null},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32,"area":null},{"id":"2405.15189","title":"EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization","created":"2024-05-24","cited_by_count":30,"area":null},{"id":"2306.00108","title":"Better patching using LLM prompting, via Self-Consistency","created":"2023-05-31","cited_by_count":29,"area":"lr"},{"id":"2606.06324","title":"From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws","created":"2026-06-04","cited_by_count":29,"area":"agents"},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"id":"2502.01821","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","created":"2025-02-03","cited_by_count":22,"area":"agents"},{"id":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19,"area":null},{"id":"2407.16235","title":"Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection","created":"2024-07-23","cited_by_count":18,"area":null},{"id":"2509.01835","title":"From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs","created":"2025-09-01","cited_by_count":18,"area":"agents"},{"id":"2410.10209","title":"EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning","created":"2024-10-14","cited_by_count":17,"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":"2402.00093","title":"ChIRAAG: ChatGPT Informed Rapid and Automated Assertion Generation","created":"2024-01-31","cited_by_count":16,"area":null},{"id":"2402.06598","title":"CigaR: Cost-efficient Program Repair with LLMs","created":"2024-02-09","cited_by_count":15,"area":null},{"id":"2311.02433","title":"Can ChatGPT support software verification?","created":"2023-11-04","cited_by_count":14,"area":null},{"id":"2410.09997","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2311.13721","title":"Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning","created":"2023-11-22","cited_by_count":12,"area":null},{"id":"2404.08877","title":"Aligning the Objective of LLM-based Program Repair","created":"2024-04-13","cited_by_count":12,"area":null},{"id":"2311.04926","title":"More Robots are Coming: Large Multimodal Models (ChatGPT) can Solve Visually Diverse Images of Parsons Problems","created":"2023-11-03","cited_by_count":11,"area":"mllm"},{"id":"2402.15100","title":"Studying LLM Performance on Closed- and Open-source Data","created":"2024-02-23","cited_by_count":11,"area":null},{"id":"2406.11589","title":"CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents","created":"2024-06-17","cited_by_count":11,"area":"agents"},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2305.02230","title":"Can ChatGPT Pass An Introductory Level Functional Language Programming Course?","created":"2023-04-29","cited_by_count":9,"area":null},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2408.12056","title":"Enhancing Automated Program Repair with Solution Design","created":"2024-08-22","cited_by_count":8,"area":null},{"id":"2506.17208","title":"Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems","created":"2025-06-20","cited_by_count":8,"area":"agents"},{"id":"2303.10494","title":"Revisiting the Plastic Surgery Hypothesis via Large Language Models","created":"2023-03-18","cited_by_count":7,"area":null},{"id":"2407.03611","title":"An Empirical Study on Capability of Large Language Models in Understanding Code Semantics","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2505.02931","title":"The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models","created":"2025-05-05","cited_by_count":7,"area":null},{"id":"2311.16017","title":"Decoding Logic Errors: A Comparative Study on Bug Detection by Students and Large Language Models","created":"2023-11-27","cited_by_count":6,"area":null},{"id":"2401.16310","title":"An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors","created":"2024-01-29","cited_by_count":6,"area":"lr"},{"id":"2312.04986","title":"Out of Context: How important is Local Context in Neural Program Repair?","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2310.16253","title":"ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2407.19610","title":"Mixture of Modular Experts: Distilling Knowledge from a Multilingual Teacher into Specialized Modular Language Models","created":"2024-07-28","cited_by_count":4,"area":"moe"},{"id":"2409.12020","title":"Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2504.20412","title":"kAgent: An execution-guided crash resolution agent for the Linux kernel","created":"2025-04-29","cited_by_count":4,"area":"agents"},{"id":"2505.17703","title":"Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.17772","title":"PAGENT: Learning to Patch Software Engineering Agents","created":"2025-06-21","cited_by_count":4,"area":"agents"},{"id":"2401.07994","title":"Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2410.07573","title":"RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?","created":"2024-10-10","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":"2507.19909","title":"The Impact of Fine-tuning Large Language Models on Automated Program Repair","created":"2025-07-26","cited_by_count":3,"area":null},{"id":"2505.10375","title":"Are Sparse Autoencoders Useful for Java Function Bug Detection?","created":"2025-05-15","cited_by_count":2,"area":"mechinterp"},{"id":"2505.13008","title":"Adversarial Reasoning for Repair Based on Inferred Program Intent","created":"2025-05-19","cited_by_count":2,"area":"lr"},{"id":"2509.10436","title":"RefactorCoderQA: Benchmarking LLMs for Multi-Domain Coding Question Solutions in Cloud and Edge Deployment","created":"2025-09-12","cited_by_count":2,"area":"moe"},{"id":"2602.06090","title":"SVRepair: Structured Visual Reasoning for Automated Program Repair","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2510.16059","title":"SIADAFIX: issue description response for adaptive program repair","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2605.09134","title":"BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models","created":"2026-05-09","cited_by_count":1,"area":"alignment"},{"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":"2507.05272","title":"LLMs and Fuzzing in Tandem: A New Approach to Automatically Generating Weakest Preconditions","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2509.19136","title":"On the Soundness and Consistency of LLM Agents for Executing Test Cases Written in Natural Language","created":"2025-09-23","cited_by_count":0,"area":"agents"},{"id":"2601.22461","title":"Toward Non-Expert Customized Congestion Control: Large Language Model-Assisted CCA Code Generation with eBPF Deployment","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.02554","title":"BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.06723","title":"Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2607.28871","title":"Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?","created":"2026-07-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}