{"total":78,"rows":[{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2507.06229","title":"Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving","created":"2025-07-08","cited_by_count":94,"area":"agents"},{"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":"2311.09835","title":"ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code","created":"2023-11-16","cited_by_count":65,"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":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52,"area":"agents"},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"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":"2407.16732","title":"PyBench: Evaluating LLM Agent on various real-world coding tasks","created":"2024-07-23","cited_by_count":24,"area":"agents"},{"id":"2410.18792","title":"An LLM Agent for Automatic Geospatial Data Analysis","created":"2024-10-24","cited_by_count":21,"area":"agents"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2509.23988","title":"LLM/Agent-as-Data-Analyst: A Survey","created":"2025-09-28","cited_by_count":16,"area":"agents"},{"id":"2502.06111","title":"CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories","created":"2025-02-10","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":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2602.01655","title":"ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development","created":"2026-02-02","cited_by_count":12,"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":"2504.04220","title":"AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation","created":"2025-04-05","cited_by_count":8,"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":"2408.01055","title":"Towards Agentic Runtime Healing","created":"2024-08-02","cited_by_count":7,"area":"agents"},{"id":"2504.07634","title":"Agent That Debugs: Dynamic State-Guided Vulnerability Repair","created":"2025-04-10","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":"2511.03404","title":"Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling","created":"2025-11-05","cited_by_count":6,"area":"agents"},{"id":"2602.16819","title":"Hybrid-Gym: Training Coding Agents to Generalize Across Tasks","created":"2026-02-18","cited_by_count":6,"area":"agents"},{"id":"2603.27277","title":"Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP","created":"2026-03-28","cited_by_count":6,"area":"agents"},{"id":"2605.08386","title":"SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents","created":"2026-05-08","cited_by_count":6,"area":"agents"},{"id":"2605.20563","title":"Multi-agent Collaboration with State Management","created":"2026-05-19","cited_by_count":6,"area":"agents"},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2606.14066","title":"FastContext: Training Efficient Repository Explorer for Coding Agents","created":"2026-06-12","cited_by_count":5,"area":"agents"},{"id":"2607.27250","title":"Do Context Files Help Coding Agents? A Two-Agent Ablation Study on Real Repositories","created":"2026-07-28","cited_by_count":5,"area":"agents"},{"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":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2601.10112","title":"Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants","created":"2026-01-15","cited_by_count":4,"area":"agents"},{"id":"2603.13258","title":"Your Code Agent Can Grow Alongside You with Structured Memory","created":"2026-02-25","cited_by_count":4,"area":"agents"},{"id":"2606.22082","title":"CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation","created":"2026-06-20","cited_by_count":4,"area":"agents"},{"id":"2510.17925","title":"SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion","created":"2025-10-20","cited_by_count":3,"area":"agents"},{"id":"2601.06268","title":"Automated QoR improvement in OpenROAD with coding agents","created":"2026-01-09","cited_by_count":3,"area":"agents"},{"id":"2605.06445","title":"Constraint Decay: The Fragility of LLM Agents in Backend Code Generation","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2608.19854","title":"Repo0: Design-Driven Zero-to-All Code Generation","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2604.02665","title":"AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits","created":"2026-04-03","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":"2606.22417","title":"Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2606.30296","title":"ManimAgent: Self-Evolving Multimodal Agents for Visual Education","created":"2026-06-29","cited_by_count":2,"area":"agents"},{"id":"2607.12161","title":"Token Reduction Is Not Cost Reduction","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2607.18213","title":"SWE-Pruner Pro: The Coder LLM Already Knows What to Prune","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2511.21380","title":"Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions","created":"2025-11-26","cited_by_count":1,"area":"agents"},{"id":"2602.13723","title":"Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspective","created":"2026-02-14","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":"2603.25928","title":"TheBotCompany: Self-Organizing Multi-agent Systems for Continuous Software Development","created":"2026-03-26","cited_by_count":1,"area":"agents"},{"id":"2603.26270","title":"Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization","created":"2026-03-27","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":"2606.03618","title":"Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.13763","title":"Do programming languages still matter to your AI coding agent teammate? Evidence at scale from chess engines","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2606.26979","title":"How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2607.02520","title":"AutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2609.04167","title":"SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2508.20119","title":"LLM Agents for Generating Microservice-based Applications: how complex is your specification?","created":"2025-08-22","cited_by_count":0,"area":"agents"},{"id":"2606.05720","title":"Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2607.25431","title":"CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.20903","title":"Generation of Web Apps with Agentic IDEs: An Empirical Assessment","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.24221","title":"DeepRepoQA: Code Repository Question Answering with Deep Agent Exploration","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2608.25570","title":"Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2608.28972","title":"Legacy System Modernization with Coding Agents: A Case Study","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2608.29834","title":"You Know What I Mean: A Benchmark for Agentic Conversational Reference Grounding","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.08355","title":"RepoNav: From Snippet Retrieval to File-Centered Repository Navigation for Code Agents","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.20050","title":"The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.23570","title":"VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.29465","title":"SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.36319","title":"StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38335","title":"E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.14968","title":"SEEK: Agentic Knowledge Graph Retrieval for Secure Code Generation","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.15708","title":"SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.15964","title":"Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}