Extract context from diverse data formats for agents
Agents should analyze varied data formats, including unstructured text, to extract crucial context for task completion.
Data science agents must be able to extract context from diverse and heterogeneous data formats.
Traditional agents often rely on well-structured data like CSVs. DS-STAR includes a data file analysis module that automatically extracts context from various formats, including unstructured ones like JSON, text, and markdown, which are common in real-world applications.
An agent processing customer feedback should be able to extract insights from both structured survey responses (CSVs) and unstructured text comments (text files).
Data science agents need to handle diverse data formats beyond simple CSVs. Extracting context from unstructured data like JSON, text, and markdown is crucial for real-world applications and improving agent versatility.
If your data is exclusively well-structured and limited to formats like CSV or SQL tables, this specific capability might be less critical.
- DS-STAR: A state-of-the-art versatile data science agent ↗Google Research Blog · Google Research Blog · Nov 6, 2025 · paraphrased
First seen on Subvolts Nov 6, 2025. Updated Sep 11, 2026. Spotted a problem? Tell us.
- DS-STAR: A state-of-the-art versatile data science agentGoogle · Google Research Blog · Nov 6, 2025
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- HeuristicIterative refinement for data science agent planningRefine data science agent plans iteratively using a judge and router to improve solutions and handle complexity. · 5 min
- ComparisonCost-effectiveness of AI models on geospatial tasksOpen-weight models like DeepSeek V3.2 offer high capability at a significantly lower cost compared to proprietary models. · 60 min
- HeuristicTask demands correlate with success, but success signatures are model-specificSimpler tasks correlate with success, but how models succeed varies. · 10 min
- ToolGameLogicBench for evaluating AI game logic codingA benchmark to evaluate AI agents on runtime game logic with tick-level state assertions in Godot projects. · 10 min
- WorkflowDS-STAR iterative planning, implementation, and verification loopAn iterative loop for data science agents: plan, code, verify, and refine until a satisfactory solution is reached. · 30 min
- HeuristicSelf-Scaling Benchmarks for Coding AgentsBenchmarks should create tasks at evaluation time to prevent data leakage and adapt difficulty based on agent performance. · 5 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with in the sources.
- Where did this come from?
- Google Research Blog (Google Research Blog). Subvolts collected, normalized and credited it; the link above opens the original.