Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses

cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/DEEP-PolyU/Awesome-Data-Agents

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications
• CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
• A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models
• 6GAgentGym: Tool Use, Data Synthesis, and Agentic Learning for Network Management
• CoDA: Agentic Systems for Collaborative Data Visualization
• RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
• TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning
• Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
• Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
• Autonomous Data Agents: A New Opportunity for Smart Data
• An LLM Agent-Based Complex Semantic Table Annotation Approach
• FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness
• Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning
• HARMON-E: Hierarchical Agentic Reasoning for Multimodal Oncology Notes to Extract Structured Data
• ToolCritic: Detecting and Correcting Tool-Use Errors in Dialogue Systems
• Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities
• Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm
• InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
• SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL
• Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems