{"total":35,"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":"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":"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":"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":"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":"2503.14713","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":"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":"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":"2602.00409","title":"Are Coding Agents Generating Over-Mocked Tests? An Empirical Study","created":"2026-01-30","cited_by_count":6,"area":"agents"},{"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":"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":"2511.18249","title":"LLM Assisted Coding with Metamorphic Specification Mutation Agent","created":"2025-11-23","cited_by_count":1,"area":"agents"},{"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":"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":"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":"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":"2602.13987","title":"ATTest: Agent-Driven Tensor Testing for Deep Learning Library Modules","created":"2026-02-15","cited_by_count":0,"area":"agents"},{"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":"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":"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"}],"next_cursor":null}