Search papers, labs, and topics across Lattice.
DataFactory is a multi-agent framework designed to overcome limitations of LLMs in Table Question Answering (TableQA) by addressing context length constraints, hallucination, and single-agent reasoning limitations. It employs a Data Leader using the ReAct paradigm to orchestrate Database and Knowledge Graph agent teams, enabling decomposition of complex queries into structured and relational reasoning tasks. Experiments across TabFact, WikiTableQuestions, and FeTaQA show DataFactory improves accuracy by up to 23.9% over baselines, with significant gains from team coordination.
LLMs can now tackle complex table QA with 20%+ accuracy gains, thanks to a multi-agent framework that decomposes queries and orchestrates reasoning between specialized database and knowledge graph agents.
Table Question Answering (TableQA) enables natural language interaction with structured tabular data. However, existing large language model (LLM) approaches face critical limitations: context length constraints that restrict data handling capabilities, hallucination issues that compromise answer reliability, and single-agent architectures that struggle with complex reasoning scenarios involving semantic relationships and multi-hop logic. This paper introduces DataFactory, a multi-agent framework that addresses these limitations through specialized team coordination and automated knowledge transformation. The framework comprises a Data Leader employing the ReAct paradigm for reasoning orchestration, together with dedicated Database and Knowledge Graph teams, enabling the systematic decomposition of complex queries into structured and relational reasoning tasks. We formalize automated data-to-knowledge graph transformation via the mapping function T:D x S x R ->G, and implement natural language-based consultation that - unlike fixed workflow multi-agent systems - enables flexible inter-agent deliberation and adaptive planning to improve coordination robustness. We also apply context engineering strategies that integrate historical patterns and domain knowledge to reduce hallucinations and improve query accuracy. Across TabFact, WikiTableQuestions, and FeTaQA, using eight LLMs from five providers, results show consistent gains. Our approach improves accuracy by 20.2% (TabFact) and 23.9% (WikiTQ) over baselines, with significant effects (Cohen's d>1). Team coordination also outperforms single-team variants (+5.5% TabFact, +14.4% WikiTQ, +17.1% FeTaQA ROUGE-2). The framework offers design guidelines for multi-agent collaboration and a practical platform for enterprise data analysis through integrated structured querying and graph-based knowledge representation.