TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning
Quick Answer
TabClaw is an open-source interactive AI agent designed for spreadsheet manipulation and table reasoning, enhancing task completion and reasoning performance.
Quick Take
It clarifies user intent, manages multi-table comparisons, and personalizes workflows based on user feedback, significantly improving efficiency in data analysis tasks.
Key Points
- TabClaw supports CSV and Excel file uploads for natural-language requests.
- It features an editable execution plan and a ReAct-style analysis loop.
- The agent records workflows and extracts user memory for personalized assistance.
- Experiments show improved task completion and reasoning performance.
- TabClaw adapts to user preferences over time through feedback.
Paper Resources
Source Excerpt
Spreadsheets and tables are widely used representations for structured data analysis, but effective analysis still requires substantial manual effort and domain expertise. Recent (LLM) agents can automate parts of this process, but they often provide limited transparency into intermediate decisions, rely on implicit assumptions, struggle with multi-table comparison, and repeat similar workflows without adapting to a user's preferences. This paper presents TabClaw, an open-so
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.