{"total":96,"rows":[{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133,"area":"agents"},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2403.16218","title":"CoverUp: Effective High Coverage Test Generation for Python","created":"2024-03-24","cited_by_count":38,"area":null},{"id":"2310.15991","title":"WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2501.12862","title":"Mutation-Guided LLM-based Test Generation at Meta","created":"2025-01-22","cited_by_count":25,"area":null},{"id":"2501.17167","title":"QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks","created":"2025-01-20","cited_by_count":22,"area":"agents"},{"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":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2508.13143","title":"Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks","created":"2025-08-18","cited_by_count":20,"area":"agents"},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"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":"2606.28434","title":"SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents","created":"2026-06-26","cited_by_count":15,"area":"agents"},{"id":"2502.18474","title":"A Contemporary Survey of Large Language Model Assisted Program Analysis","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2410.23074","title":"Multi-Programming Language Sandbox for LLMs","created":"2024-10-30","cited_by_count":10,"area":null},{"id":"2503.15554","title":"Rethinking the Evaluation of Secure Code Generation","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2409.08692","title":"B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2409.13642","title":"A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion","created":"2024-09-20","cited_by_count":9,"area":"agents"},{"id":"2503.13580","title":"LLM Test Generation via Iterative Hybrid Program Analysis","created":"2025-03-17","cited_by_count":9,"area":null},{"id":"2503.14713","title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","created":"2025-03-18","cited_by_count":9,"area":"agents"},{"id":"2506.02943","title":"Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation","created":"2025-06-03","cited_by_count":9,"area":"agents"},{"id":"2408.07846","title":"A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites","created":"2024-08-14","cited_by_count":8,"area":null},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2409.12682","title":"Retrieval-Augmented Test Generation: How Far Are We?","created":"2024-09-19","cited_by_count":7,"area":"rag"},{"id":"2602.08146","title":"Test vs Mutant: Adversarial LLM Agents for Robust Unit Test Generation","created":"2026-02-08","cited_by_count":7,"area":"agents"},{"id":"2501.11086","title":"Evaluating LLM-Based Regression Test Generation","created":"2025-01-19","cited_by_count":6,"area":null},{"id":"2502.07487","title":"Multi-Agent Collaboration for Multilingual Code Instruction Tuning","created":"2025-02-11","cited_by_count":6,"area":"agents"},{"id":"2510.03588","title":"REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement","created":"2025-10-04","cited_by_count":6,"area":"agents"},{"id":"2512.08967","title":"CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing","created":"2025-12-01","cited_by_count":6,"area":"safety"},{"id":"2602.00409","title":"Are Coding Agents Generating Over-Mocked Tests? An Empirical Study","created":"2026-01-30","cited_by_count":6,"area":"agents"},{"id":"2601.08734","title":"TerraFormer: Automated Infrastructure-as-Code with LLMs Fine-Tuned via Policy-Guided Verifier Feedback","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2602.00746","title":"Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression","created":"2026-01-31","cited_by_count":5,"area":"mllm"},{"id":"2502.16071","title":"Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models","created":"2025-02-22","cited_by_count":4,"area":"rag"},{"id":"2506.07313","title":"SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows","created":"2025-06-08","cited_by_count":4,"area":"agents"},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2505.17928","title":"Towards Practical Defect-Focused Automated Code Review","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2601.09703","title":"ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation","created":"2026-01-14","cited_by_count":3,"area":"inference"},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2405.03509","title":"Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context Learning","created":"2024-05-06","cited_by_count":2,"area":"lr"},{"id":"2505.12424","title":"EvoGPT: Leveraging LLM-Driven Seed Diversity to Improve Search-Based Test Suite Generation","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.01104","title":"HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"lr"},{"id":"2603.15921","title":"VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2607.06195","title":"LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle","created":"2026-07-07","cited_by_count":2,"area":"agents"},{"id":"2502.01273","title":"Analysis of Student-LLM Interaction in a Software Engineering Project","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.02866","title":"A Systematic Approach for Assessing Large Language Models' Test Case Generation Capability","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2504.17203","title":"High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2506.10998","title":"Towards Automated Formal Verification of Backend Systems with LLMs","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2506.15648","title":"deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2508.02503","title":"OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical Modeling","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2509.12987","title":"Toward PDDL Planning Copilot","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2509.23812","title":"Navigating the Labyrinth: Path-Sensitive Unit Test Generation with Large Language Models","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2511.18249","title":"LLM Assisted Coding with Metamorphic Specification Mutation Agent","created":"2025-11-23","cited_by_count":1,"area":"agents"},{"id":"2511.20403","title":"LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.22832","title":"Just-in-Time Catching Test Generation at Meta","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.20684","title":"Agile V: A Compliance-Ready Framework for AI-Augmented Engineering -- From Concept to Audit-Ready Delivery","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2602.21997","title":"Enhancing LLM-Based Test Generation by Eliminating Covered Code","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2604.05159","title":"Planning to Explore: Curiosity-Driven Planning for LLM Test Generation","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.10126","title":"MR-Coupler: Automated Metamorphic Test Generation via Functional Coupling Analysis","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2605.06125","title":"Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.15229","title":"PBT-Bench: Benchmarking AI Agents on Property-Based Testing","created":"2026-05-13","cited_by_count":1,"area":"agents"},{"id":"2607.08983","title":"SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2607.09123","title":"ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports","created":"2026-07-10","cited_by_count":1,"area":"agents"},{"id":"2607.13111","title":"SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2503.17837","title":"A Study on the Improvement of Code Generation Quality Using Large Language Models Leveraging Product Documentation","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2504.15286","title":"CUBETESTERAI: Automated JUnit Test Generation using the LLaMA Model","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2505.17207","title":"Content Moderation in TV Search: Balancing Policy Compliance, Relevance, and User Experience","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2506.11081","title":"SAGE:Specification-Aware Grammar Extraction for Automated Test Case Generation with LLMs","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2507.16037","title":"A Pilot Study on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights","created":"2025-07-21","cited_by_count":0,"area":"agents"},{"id":"2508.09791","title":"LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations","created":"2025-08-13","cited_by_count":0,"area":"rag"},{"id":"2508.16071","title":"From Benchmark Data To Applicable Program Repair: An Experience Report","created":"2025-08-22","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":"2510.13248","title":"Automated Network Protocol Testing with LLM Agents","created":"2025-10-15","cited_by_count":0,"area":"agents"},{"id":"2510.15494","title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.01010","title":"Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis","created":"2025-11-30","cited_by_count":0,"area":"agents"},{"id":"2512.06247","title":"DUET: Agentic Design Understanding via Experimentation and Testing","created":"2025-12-06","cited_by_count":0,"area":"agents"},{"id":"2601.18241","title":"TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.13987","title":"ATTest: Agent-Driven Tensor Testing for Deep Learning Library Modules","created":"2026-02-15","cited_by_count":0,"area":"agents"},{"id":"2602.16671","title":"SPARC: Scenario Planning and Reasoning for Automated C Unit Test Generation","created":"2026-02-18","cited_by_count":0,"area":"lr"},{"id":"2604.03135","title":"AI-Assisted Unit Test Writing and Test-Driven Code Refactoring: A Case Study","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.15270","title":"Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation","created":"2026-04-16","cited_by_count":0,"area":"rag"},{"id":"2605.00942","title":"PPO guided Agentic Pipeline for Adaptive Prompt Selection and Test Case Generation","created":"2026-05-01","cited_by_count":0,"area":"agents"},{"id":"2605.01264","title":"FeedbackLLM: Metadata driven Multi-Agentic Language Agnostic Test Case Generator with Evolving prompt and Coverage Feedback","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.01471","title":"Practical Limits of Autonomous Test Repair: A Multi-Agent Case Study with LLM-Driven Discovery and Self-Correction","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.09573","title":"ConCovUp: Effective Agent-Based Test Driver Generation for Concurrency Testing","created":"2026-05-10","cited_by_count":0,"area":"agents"},{"id":"2605.27981","title":"STAB: Specification-driven Testing for Algorithmic Bottlenecks","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.29822","title":"Inferring Code Correctness from Specification","created":"2026-05-28","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":"2607.09101","title":"Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.22880","title":"Do Coverage and Mutation Scores of LLM-Generated Test Suites Correlate with Their Effectiveness? (Replicability Study)","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.22883","title":"Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.05822","title":"Agent-Based Test Assertion Generation via Diverse Perspective Aggregation","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"id":"2609.05978","title":"VibeCheck: Assessing the Quality of LLM-Generated Unit Tests: A Multi-agent Empirical Study across Heterogeneous Repositories","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2610.04921","title":"Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.13626","title":"SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}