{"total":102,"rows":[{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2410.05080","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","created":"2024-10-07","cited_by_count":235,"area":"agents"},{"id":"2402.18679","title":"Data Interpreter: An LLM Agent For Data Science","created":"2024-02-28","cited_by_count":225,"area":"agents"},{"id":"2406.09961","title":"ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation","created":"2024-06-14","cited_by_count":129,"area":"lr"},{"id":"2510.16872","title":"DeepAnalyze: Agentic Large Language Models for Autonomous Data Science","created":"2025-10-19","cited_by_count":50,"area":"agents"},{"id":"2406.12934","title":"Current state of LLM Risks and AI Guardrails","created":"2024-06-16","cited_by_count":46,"area":"safety"},{"id":"2502.17651","title":"METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling","created":"2025-02-24","cited_by_count":34,"area":"lr"},{"id":"2505.11935","title":"ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing","created":"2025-05-17","cited_by_count":32,"area":"mllm"},{"id":"2510.23587","title":"A Survey of Data Agents: Emerging Paradigm or Overstated Hype?","created":"2025-10-27","cited_by_count":30,"area":"agents"},{"id":"2601.23265","title":"PaperBanana: Automating Academic Illustration for AI Scientists","created":"2026-01-30","cited_by_count":26,"area":null},{"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":"2407.16732","title":"PyBench: Evaluating LLM Agent on various real-world coding tasks","created":"2024-07-23","cited_by_count":24,"area":"agents"},{"id":"2502.19400","title":"TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2412.02764","title":"Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code","created":"2024-12-03","cited_by_count":23,"area":null},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"area":"agents"},{"id":"2602.03828","title":"AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations","created":"2026-02-03","cited_by_count":23,"area":null},{"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":"2506.02454","title":"Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework","created":"2025-06-03","cited_by_count":21,"area":"agents"},{"id":"2502.00988","title":"PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback","created":"2025-02-03","cited_by_count":20,"area":"agents"},{"id":"2508.06492","title":"Effective Training Data Synthesis for Improving MLLM Chart Understanding","created":"2025-08-08","cited_by_count":20,"area":"synth"},{"id":"2508.13587","title":"Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation","created":"2025-08-19","cited_by_count":19,"area":"lr"},{"id":"2601.04498","title":"IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation","created":"2026-01-08","cited_by_count":17,"area":null},{"id":"2508.17608","title":"ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning","created":"2025-08-25","cited_by_count":16,"area":null},{"id":"2510.03194","title":"CoDA: Agentic Systems for Collaborative Data Visualization","created":"2025-10-03","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":"2412.04272","title":"PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables","created":"2024-12-05","cited_by_count":14,"area":"lr"},{"id":"2603.06674","title":"AutoFigure-Edit: Generating Editable Scientific Illustration","created":"2026-03-03","cited_by_count":14,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2505.20538","title":"AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy","created":"2025-05-26","cited_by_count":13,"area":null},{"id":"2504.02906","title":"Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement","created":"2025-04-03","cited_by_count":11,"area":"mllm"},{"id":"2505.07064","title":"ParaView-MCP: An Autonomous Visualization Agent with Direct Tool Use","created":"2025-05-11","cited_by_count":11,"area":"agents"},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2603.29139","title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents","created":"2026-03-31","cited_by_count":10,"area":"agents"},{"id":"2506.13326","title":"VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2510.23538","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","created":"2025-10-27","cited_by_count":9,"area":null},{"id":"2503.07044","title":"DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation","created":"2025-03-10","cited_by_count":8,"area":"agents"},{"id":"2507.21124","title":"VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization","created":"2025-07-18","cited_by_count":8,"area":"agents"},{"id":"2601.04390","title":"SciFig: Towards Automating Editable Figure Generation for Scientific Papers","created":"2026-01-07","cited_by_count":8,"area":null},{"id":"2502.08056","title":"Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2502.11140","title":"Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven Optimization","created":"2025-02-16","cited_by_count":7,"area":"lr"},{"id":"2602.13294","title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","created":"2026-02-09","cited_by_count":7,"area":"lr"},{"id":"2410.18652","title":"$C^2$: Scalable Auto-Feedback for LLM-based Chart Generation","created":"2024-10-24","cited_by_count":6,"area":null},{"id":"2509.15160","title":"An Evaluation-Centric Paradigm for Scientific Visualization Agents","created":"2025-09-18","cited_by_count":6,"area":"agents"},{"id":"2510.23642","title":"VisCoder2: Building Multi-Language Visualization Coding Agents","created":"2025-10-24","cited_by_count":6,"area":"agents"},{"id":"2604.06079","title":"Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning","created":"2026-04-07","cited_by_count":6,"area":"lr"},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2505.16832","title":"From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2507.14306","title":"Manimator: Transforming Research Papers into Visual Explanations","created":"2025-07-18","cited_by_count":5,"area":null},{"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":"2502.16395","title":"AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science","created":"2025-02-23","cited_by_count":4,"area":null},{"id":"2504.04855","title":"BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents","created":"2025-04-07","cited_by_count":4,"area":"agents"},{"id":"2510.09724","title":"InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2510.15951","title":"Attention to Non-Adopters","created":"2025-10-10","cited_by_count":4,"area":null},{"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":"2607.01883","title":"PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation","created":"2026-07-02","cited_by_count":4,"area":null},{"id":"2507.08719","title":"Multilingual Multimodal Software Developer for Code Generation","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2510.03341","title":"OpusAnimation: Code-Based Dynamic Chart Generation","created":"2025-10-02","cited_by_count":3,"area":null},{"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":"2603.25063","title":"TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization","created":"2026-03-26","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":"2512.13297","title":"MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2601.15153","title":"How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework","created":"2026-01-21","cited_by_count":2,"area":"agents"},{"id":"2604.24559","title":"Aligned Multi-View Scripts for Universal Chart-to-Code Generation","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2604.27996","title":"Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization","created":"2026-04-30","cited_by_count":2,"area":"agents"},{"id":"2606.03841","title":"EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.06416","title":"Unsupervised Skill Discovery for Agentic Data Analysis","created":"2026-06-04","cited_by_count":2,"area":"agents"},{"id":"2606.26614","title":"HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization","created":"2026-06-25","cited_by_count":2,"area":"agents"},{"id":"2509.09245","title":"Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search","created":"2025-09-11","cited_by_count":1,"area":null},{"id":"2510.09390","title":"Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.21920","title":"Toward Automated and Trustworthy Scientific Analysis and Visualization with LLM-Generated Code","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2512.01017","title":"ChartAnchor: Chart Grounding with Structural-Semantic Fidelity","created":"2025-11-30","cited_by_count":1,"area":"mllm"},{"id":"2601.04204","title":"TeachMaster: Generative Teaching via Code","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2602.12311","title":"Perceptual Self-Reflection in Agentic Physics Simulation Code Generation","created":"2026-02-12","cited_by_count":1,"area":"agents"},{"id":"2603.16873","title":"The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality","created":"2026-01-26","cited_by_count":1,"area":"agents"},{"id":"2605.00800","title":"Generating Statistical Charts with Validation-Driven LLM Workflows","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2608.03298","title":"SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2609.01409","title":"EdiTikZ: Scientific Figure Editing from Revision Trajectories","created":"2026-09-01","cited_by_count":1,"area":"mllm"},{"id":"2609.29718","title":"PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2503.22388","title":"Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2511.11933","title":"InData: Towards Secure Multi-Step, Tool-Based Data Analysis","created":"2025-11-14","cited_by_count":0,"area":"agents"},{"id":"2512.06859","title":"JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models","created":"2025-12-07","cited_by_count":0,"area":"lr"},{"id":"2512.12063","title":"Instruction-Tuning Open-Weight Language Models for BPMN Model Generation","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2602.05353","title":"AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2603.16057","title":"Toward Reliable Scientific Visualization Pipeline Construction with Structure-Aware Retrieval-Augmented LLMs","created":"2026-03-17","cited_by_count":0,"area":"rag"},{"id":"2604.02794","title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.15319","title":"Explainable Iterative Data Visualisation Refinement via an LLM Agent","created":"2026-03-02","cited_by_count":0,"area":"agents"},{"id":"2605.15585","title":"See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.11176","title":"Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.17915","title":"Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization","created":"2026-06-16","cited_by_count":0,"area":"agents"},{"id":"2607.19910","title":"MV-Bench: Benchmarking Multimodal Large Language Models for Coordinated Multi-View Interface Construction","created":"2026-07-22","cited_by_count":0,"area":"mllm"},{"id":"2608.03464","title":"ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation Generation","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.15510","title":"Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.26757","title":"DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.00714","title":"ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.08155","title":"SciFigure2Code: An AI-Reconstructed Benchmark for Scientific Figure-to-Code","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.32528","title":"Fail Loudly: An Auditable Runtime for Agentic Data Analysis","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.35255","title":"Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38642","title":"ChartRevise: A Dataset and Evaluation Protocol for Exact Chart Editing via Code","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":"100"}