{"total":126,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035,"area":"agents"},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564,"area":"agents"},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469,"area":"agents"},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336,"area":"agents"},{"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":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2505.20411","title":"SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents","created":"2025-05-26","cited_by_count":142,"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":"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":"2312.11671","title":"Evaluating Language-Model Agents on Realistic Autonomous Tasks","created":"2023-12-18","cited_by_count":96,"area":"agents"},{"id":"2504.00587","title":"AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems","created":"2025-04-01","cited_by_count":90,"area":"agents"},{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85,"area":"agents"},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"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":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61,"area":"agents"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"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":"2509.07506","title":"Astra: A Multi-Agent System for GPU Kernel Performance Optimization","created":"2025-09-09","cited_by_count":51,"area":"agents"},{"id":"2504.00255","title":"SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers","created":"2025-03-31","cited_by_count":43,"area":"agents"},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2505.07782","title":"MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering","created":"2025-05-12","cited_by_count":41,"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":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"id":"2411.01747","title":"DynaSaur: Large Language Agents Beyond Predefined Actions","created":"2024-11-04","cited_by_count":32,"area":"agents"},{"id":"2502.05664","title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","created":"2025-02-08","cited_by_count":32,"area":"agents"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2308.04030","title":"Gentopia: A Collaborative Platform for Tool-Augmented LLMs","created":"2023-08-08","cited_by_count":26,"area":"agents"},{"id":"2503.07010","title":"ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation","created":"2025-03-10","cited_by_count":26,"area":"agents"},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"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":"2406.00215","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","created":"2024-05-31","cited_by_count":24,"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":"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":"2402.01411","title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","created":"2024-02-02","cited_by_count":22,"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":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2510.25694","title":"Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents","created":"2025-10-29","cited_by_count":18,"area":"agents"},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2606.30560","title":"TraceLab: Characterizing Coding Agent Workloads for LLM Serving","created":"2026-06-29","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":"2504.21205","title":"SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories","created":"2025-04-29","cited_by_count":14,"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":"2602.17100","title":"AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation","created":"2026-02-19","cited_by_count":13,"area":"agents"},{"id":"2410.01242","title":"RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance","created":"2024-10-02","cited_by_count":12,"area":"agents"},{"id":"2506.19724","title":"From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking","created":"2025-06-24","cited_by_count":12,"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":"2602.21611","title":"Structurally Aligned Subtask-Level Memory for Software Engineering Agents","created":"2026-02-25","cited_by_count":12,"area":"agents"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","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":"2607.00053","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","created":"2026-06-30","cited_by_count":11,"area":"agents"},{"id":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"area":"agents"},{"id":"2602.01664","title":"FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing","created":"2026-02-02","cited_by_count":9,"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":"2606.11864","title":"CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding","created":"2026-06-10","cited_by_count":7,"area":"agents"},{"id":"2509.09936","title":"SciML Agents: Write the Solver, Not the Solution","created":"2025-09-12","cited_by_count":6,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2605.15377","title":"Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2603.15707","title":"SEMAG: Self-Evolutionary Multi-Agent Code Generation","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2604.00917","title":"Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time","created":"2026-04-01","cited_by_count":5,"area":"agents"},{"id":"2604.01527","title":"REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage","created":"2026-04-02","cited_by_count":5,"area":"agents"},{"id":"2606.23664","title":"MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?","created":"2026-06-22","cited_by_count":5,"area":"agents"},{"id":"2602.02262","title":"OmniCode: A Benchmark for Evaluating Software Engineering Agents","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","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":"2410.12236","title":"Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay","created":"2024-10-16","cited_by_count":3,"area":"agents"},{"id":"2509.17489","title":"MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM","created":"2025-09-22","cited_by_count":3,"area":"agents"},{"id":"2509.23675","title":"PAT-Agent: Autoformalization for Model Checking","created":"2025-09-28","cited_by_count":3,"area":"agents"},{"id":"2602.09447","title":"SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents","created":"2026-02-10","cited_by_count":3,"area":"agents"},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","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":"2605.15301","title":"Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution","created":"2026-05-14","cited_by_count":3,"area":"agents"},{"id":"2605.24693","title":"CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming","created":"2026-05-23","cited_by_count":3,"area":"agents"},{"id":"2607.19338","title":"CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents","created":"2026-07-21","cited_by_count":3,"area":"agents"},{"id":"2608.00267","title":"LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2509.00629","title":"Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?","created":"2025-08-30","cited_by_count":2,"area":"agents"},{"id":"2510.08804","title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","created":"2025-10-09","cited_by_count":2,"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":"2604.03035","title":"Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution","created":"2026-04-03","cited_by_count":2,"area":"agents"},{"id":"2605.10597","title":"CrackMeBench: Binary Reverse Engineering for Agents","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2608.03392","title":"Self-Evolving Coding Agents","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2609.04611","title":"$\\tau^\\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction","created":"2026-09-04","cited_by_count":2,"area":"agents"},{"id":"2507.18812","title":"MemoCoder: Automated Function Synthesis using LLM-Supported Agents","created":"2025-07-24","cited_by_count":1,"area":"agents"},{"id":"2507.23336","title":"DSBC : Data Science task Benchmarking with Context engineering","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2511.20709","title":"DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents","created":"2025-11-24","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":"2603.03233","title":"AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework","created":"2026-03-03","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":"2605.02431","title":"ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation","created":"2026-05-04","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":"2605.23574","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":"2606.10933","title":"Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2608.01234","title":"Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination","created":"2026-08-02","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}