{"total":42,"rows":[{"id":"2505.03733","title":"WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch","created":"2025-05-06","cited_by_count":72,"area":"agents"},{"id":"2501.07531","title":"Evaluating Agent-based Program Repair at Google","created":"2025-01-13","cited_by_count":35,"area":"agents"},{"id":"2602.05892","title":"ContextBench: A Benchmark for Context Retrieval in Coding Agents","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2511.12884","title":"Agent READMEs: An Empirical Study of Context Files for Agentic Coding","created":"2025-11-17","cited_by_count":23,"area":"agents"},{"id":"2502.13767","title":"Agentic AI Software Engineers: Programming with Trust","created":"2025-02-19","cited_by_count":20,"area":"agents"},{"id":"2506.14683","title":"Unified Software Engineering Agent as AI Software Engineer","created":"2025-06-17","cited_by_count":19,"area":"agents"},{"id":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16,"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":"2503.12374","title":"Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios","created":"2025-03-16","cited_by_count":14,"area":"agents"},{"id":"2508.17343","title":"Agentic AI for Software: thoughts from Software Engineering community","created":"2025-08-24","cited_by_count":10,"area":"agents"},{"id":"2505.08120","title":"Putting It All into Context: Simplifying Agents with LCLMs","created":"2025-05-12","cited_by_count":9,"area":"agents"},{"id":"2506.16650","title":"SemAgent: A Semantics Aware Program Repair Agent","created":"2025-06-19","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2602.22764","title":"Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents","created":"2026-02-26","cited_by_count":8,"area":"agents"},{"id":"2507.18755","title":"Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback","created":"2025-07-24","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":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2601.19066","title":"Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2510.03217","title":"Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair","created":"2025-10-03","cited_by_count":5,"area":"agents"},{"id":"2604.06861","title":"REAgent: Requirement-Driven LLM Agents for Software Issue Resolution","created":"2026-04-08","cited_by_count":4,"area":"agents"},{"id":"2501.07892","title":"Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models","created":"2025-01-14","cited_by_count":3,"area":"agents"},{"id":"2511.08475","title":"Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale","created":"2025-11-11","cited_by_count":3,"area":"agents"},{"id":"2605.27238","title":"EviACT: An Evidence-to-Action Framework for Agentic Program Repair","created":"2026-05-26","cited_by_count":3,"area":"agents"},{"id":"2608.11386","title":"The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2609.09133","title":"ExecCritic: Learn to Test, Test to Improve for Coding Agents","created":"2026-09-08","cited_by_count":3,"area":"agents"},{"id":"2511.11012","title":"Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair","created":"2025-11-14","cited_by_count":2,"area":"agents"},{"id":"2601.13933","title":"VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2604.07341","title":"ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2605.03117","title":"ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization","created":"2026-05-04","cited_by_count":2,"area":"agents"},{"id":"2505.20973","title":"Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement","created":"2025-05-27","cited_by_count":1,"area":"agents"},{"id":"2507.22414","title":"AutoCodeSherpa: Symbolic Explanations in AI Coding Agents","created":"2025-07-30","cited_by_count":1,"area":"agents"},{"id":"2604.24212","title":"Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2607.09553","title":"Writing Bug Reports for Software Repair Agents: What Information Matters Most?","created":"2026-07-10","cited_by_count":1,"area":"agents"},{"id":"2607.12605","title":"Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2608.06811","title":"Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2609.11028","title":"BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure","created":"2026-09-10","cited_by_count":1,"area":"agents"},{"id":"2604.10300","title":"From Helpful to Trustworthy: LLM Agents for Pair Programming","created":"2026-04-11","cited_by_count":0,"area":"agents"},{"id":"2604.17464","title":"Project Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable Specifications","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2606.06752","title":"Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloomberg","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2606.18619","title":"Code-Augur: Agentic Vulnerability Detection via Specification Inference","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2607.26451","title":"ExplainBench: Evaluating Code Explanations from Agents","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2609.18805","title":"ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks","created":"2026-09-16","cited_by_count":0,"area":"agents"}],"next_cursor":null}