{"total":51,"rows":[{"id":"2401.07339","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","created":"2024-01-14","cited_by_count":282,"area":"agents"},{"id":"2401.05507","title":"InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks","created":"2024-01-10","cited_by_count":140,"area":"agents"},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2409.09030","title":"Agents in Software Engineering: Survey, Landscape, and Vision","created":"2024-09-13","cited_by_count":60,"area":"agents"},{"id":"2409.16165","title":"EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities","created":"2024-09-24","cited_by_count":52,"area":"agents"},{"id":"2505.07473","title":"Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks","created":"2025-05-12","cited_by_count":40,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2602.14337","title":"LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces","created":"2026-02-15","cited_by_count":34,"area":"agents"},{"id":"2508.18993","title":"GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging","created":"2025-08-26","cited_by_count":25,"area":"agents"},{"id":"2603.03823","title":"SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration","created":"2026-03-04","cited_by_count":23,"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":"2504.20115","title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","created":"2025-04-28","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":"2511.13998","title":"LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering","created":"2025-11-17","cited_by_count":16,"area":"agents"},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"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":"2507.00014","title":"SWE-Bench-CL: Continual Learning for Coding Agents","created":"2025-06-13","cited_by_count":14,"area":"agents"},{"id":"2408.05006","title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis","created":"2024-08-09","cited_by_count":13,"area":"agents"},{"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":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2505.21069","title":"CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software Building","created":"2025-05-27","cited_by_count":10,"area":"agents"},{"id":"2606.22902","title":"Agent-as-a-Router: Agentic Model Routing for Coding Tasks","created":"2026-06-22","cited_by_count":10,"area":"agents"},{"id":"2503.14713","title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","created":"2025-03-18","cited_by_count":9,"area":"agents"},{"id":"2509.11523","title":"VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection","created":"2025-09-15","cited_by_count":8,"area":"agents"},{"id":"2504.19277","title":"Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling","created":"2025-04-27","cited_by_count":7,"area":"agents"},{"id":"2507.23096","title":"ChatVis: Large Language Model Agent for Generating Scientific Visualizations","created":"2025-07-30","cited_by_count":7,"area":"agents"},{"id":"2510.04852","title":"FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration","created":"2025-10-06","cited_by_count":5,"area":"agents"},{"id":"2602.19547","title":"CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents","created":"2026-02-23","cited_by_count":5,"area":"agents"},{"id":"2506.00739","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","created":"2025-05-31","cited_by_count":4,"area":"agents"},{"id":"2503.07693","title":"Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"agents"},{"id":"2508.17720","title":"RepoTransAgent: Multi-Agent LLM Framework for Repository-Aware Code Translation","created":"2025-08-25","cited_by_count":3,"area":"agents"},{"id":"2604.05955","title":"Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution","created":"2026-04-07","cited_by_count":3,"area":"agents"},{"id":"2605.11269","title":"gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy","created":"2026-05-11","cited_by_count":3,"area":"agents"},{"id":"2402.02388","title":"Solution-oriented Agent-based Models Generation with Verifier-assisted Iterative In-context Learning","created":"2024-02-04","cited_by_count":2,"area":"agents"},{"id":"2607.01425","title":"Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.24882","title":"Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents","created":"2026-07-27","cited_by_count":2,"area":"agents"},{"id":"2406.16739","title":"Agent-Driven Automatic Software Improvement","created":"2024-06-24","cited_by_count":1,"area":"agents"},{"id":"2601.21115","title":"Multi-task Code LLMs: Data Mix or Model Merge?","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2603.25770","title":"ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation","created":"2026-03-26","cited_by_count":1,"area":"agents"},{"id":"2605.15334","title":"From I/O to Code with Discovery Agent","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2605.17554","title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2605.23574","title":"Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2511.02071","title":"Human-AI Co-Embodied Intelligence for Scientific Experimentation and Manufacturing","created":"2025-11-03","cited_by_count":0,"area":"agents"},{"id":"2511.11933","title":"InData: Towards Secure Multi-Step, Tool-Based Data Analysis","created":"2025-11-14","cited_by_count":0,"area":"agents"},{"id":"2603.13723","title":"Do AI Agents Really Improve Code Readability?","created":"2026-03-14","cited_by_count":0,"area":"agents"},{"id":"2604.23088","title":"Code Broker: A Multi-Agent System for Automated Code Quality Assessment","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2605.02163","title":"DocSync: Agentic Documentation Maintenance via Critic-Guided Reflexion","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2607.03968","title":"Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents","created":"2026-07-04","cited_by_count":0,"area":"agents"},{"id":"2607.15948","title":"TARS: A Theory-of-Mind Agent for Personalized In-IDE Code Comprehension","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2608.16022","title":"OpenHarmony Bench: Evaluating LLMs and Coding Agents on OpenHarmony App Development","created":"2026-08-17","cited_by_count":0,"area":"agents"}],"next_cursor":null}