{"total":112,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"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":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2406.18518","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","created":"2024-06-26","cited_by_count":198,"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":"2402.11453","title":"MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization","created":"2024-02-18","cited_by_count":102,"area":"agents"},{"id":"2311.17541","title":"TaskWeaver: A Code-First Agent Framework","created":"2023-11-29","cited_by_count":86,"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":"2508.14111","title":"From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery","created":"2025-08-18","cited_by_count":77,"area":"agents"},{"id":"2310.06830","title":"Lemur: Harmonizing Natural Language and Code for Language Agents","created":"2023-10-10","cited_by_count":72,"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":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"agents"},{"id":"2502.13897","title":"DataSciBench: An LLM Agent Benchmark for Data Science","created":"2025-02-19","cited_by_count":57,"area":"agents"},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56,"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":"2510.16872","title":"DeepAnalyze: Agentic Large Language Models for Autonomous Data Science","created":"2025-10-19","cited_by_count":50,"area":"agents"},{"id":"2406.08747","title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","created":"2024-06-13","cited_by_count":47,"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":"2407.06423","title":"InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation","created":"2024-07-08","cited_by_count":32,"area":"agents"},{"id":"2402.17168","title":"Benchmarking Data Science Agents","created":"2024-02-27","cited_by_count":30,"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":"2411.03562","title":"Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance","created":"2024-11-05","cited_by_count":25,"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":"2407.16732","title":"PyBench: Evaluating LLM Agent on various real-world coding tasks","created":"2024-07-23","cited_by_count":24,"area":"agents"},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2512.04324","title":"DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle","created":"2025-12-03","cited_by_count":23,"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":"2402.15809","title":"Empowering Large Language Model Agents through Action Learning","created":"2024-02-24","cited_by_count":22,"area":"agents"},{"id":"2412.14222","title":"A Survey on Large Language Model-based Agents for Statistics and Data Science","created":"2024-12-18","cited_by_count":22,"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":"2503.06664","title":"Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets","created":"2025-03-09","cited_by_count":20,"area":"agents"},{"id":"2403.05307","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","created":"2024-03-08","cited_by_count":17,"area":"agents"},{"id":"2509.17567","title":"LIMI: Less is More for Agency","created":"2025-09-22","cited_by_count":17,"area":"agents"},{"id":"2504.04808","title":"ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines","created":"2025-04-07","cited_by_count":16,"area":"agents"},{"id":"2601.02695","title":"EvoRoute: Experience-Driven Self-Routing LLM Agent Systems","created":"2026-01-06","cited_by_count":16,"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":"2607.08124","title":"TTHE: Test-Time Harness Evolution","created":"2026-07-09","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":"2510.01285","title":"LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science","created":"2025-09-30","cited_by_count":15,"area":"agents"},{"id":"2601.16344","title":"DSGym: A Holistic Framework for Evaluating and Training Data Science Agents","created":"2026-01-22","cited_by_count":15,"area":"agents"},{"id":"2604.28139","title":"Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows","created":"2026-04-30","cited_by_count":13,"area":"agents"},{"id":"2512.04111","title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","created":"2025-11-30","cited_by_count":12,"area":"agents"},{"id":"2602.09540","title":"SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?","created":"2026-02-10","cited_by_count":12,"area":"agents"},{"id":"2512.10398","title":"Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases","created":"2025-12-11","cited_by_count":11,"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":"2505.16100","title":"BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research","created":"2025-05-22","cited_by_count":8,"area":"agents"},{"id":"2601.21403","title":"DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis","created":"2026-01-29","cited_by_count":7,"area":"agents"},{"id":"2602.05176","title":"Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems","created":"2026-02-05","cited_by_count":7,"area":"agents"},{"id":"2602.18710","title":"Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse","created":"2026-02-21","cited_by_count":7,"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":"2406.07275","title":"DCA-Bench: A Benchmark for Dataset Curation Agents","created":"2024-06-11","cited_by_count":6,"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":"2601.02598","title":"LongDA: Benchmarking LLM Agents for Long-Document Data Analysis","created":"2026-01-05","cited_by_count":6,"area":"agents"},{"id":"2601.13591","title":"DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems","created":"2026-01-20","cited_by_count":6,"area":"agents"},{"id":"2605.14460","title":"Exploiting LLM Agent Supply Chains via Payload-less Skills","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2407.10499","title":"CIBench: Evaluating Your LLMs with a Code Interpreter Plugin","created":"2024-07-15","cited_by_count":5,"area":"agents"},{"id":"2409.06336","title":"Towards Agentic AI on Particle Accelerators","created":"2024-09-10","cited_by_count":5,"area":"agents"},{"id":"2511.08301","title":"Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning","created":"2025-11-11","cited_by_count":5,"area":"agents"},{"id":"2602.02039","title":"Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models","created":"2026-02-02","cited_by_count":5,"area":"agents"},{"id":"2604.13888","title":"GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis","created":"2026-04-15","cited_by_count":5,"area":"agents"},{"id":"2605.09698","title":"Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2505.14163","title":"DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation","created":"2025-05-20","cited_by_count":4,"area":"agents"},{"id":"2506.08800","title":"Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents","created":"2025-06-10","cited_by_count":4,"area":"agents"},{"id":"2512.04416","title":"DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows","created":"2025-12-04","cited_by_count":4,"area":"agents"},{"id":"2603.22767","title":"Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","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":"2605.30434","title":"LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2608.04968","title":"EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement","created":"2026-08-05","cited_by_count":4,"area":"agents"},{"id":"2511.22884","title":"InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents","created":"2025-11-28","cited_by_count":3,"area":"agents"},{"id":"2602.02619","title":"daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently","created":"2026-02-02","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":"2607.05174","title":"AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments","created":"2026-07-06","cited_by_count":3,"area":"agents"},{"id":"2607.07504","title":"Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows","created":"2026-07-08","cited_by_count":3,"area":"agents"},{"id":"2507.09481","title":"Evaluating LLMs on Sequential API Call Through Automated Test Generation","created":"2025-07-13","cited_by_count":2,"area":"agents"},{"id":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"id":"2511.19536","title":"AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents","created":"2025-11-24","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":"2507.23336","title":"DSBC : Data Science task Benchmarking with Context engineering","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2509.11942","title":"VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems","created":"2025-09-15","cited_by_count":1,"area":"agents"},{"id":"2602.12311","title":"Perceptual Self-Reflection in Agentic Physics Simulation Code Generation","created":"2026-02-12","cited_by_count":1,"area":"agents"},{"id":"2602.14681","title":"ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies","created":"2026-02-16","cited_by_count":1,"area":"agents"},{"id":"2605.15706","title":"Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2606.07718","title":"A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline","created":"2026-06-05","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":"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":"2608.01645","title":"GISAgentBench: A Practitioner-Sourced Benchmark for Evaluating LLM Agents on GIS Tasks","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.07147","title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"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":"2604.20727","title":"Supplement Generation Training for Enhancing Agentic Task Performance","created":"2026-04-22","cited_by_count":0,"area":"agents"},{"id":"2605.12376","title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.20690","title":"Declarative Data Services: Structured Agentic Discovery for Composing Data Systems","created":"2026-05-20","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}