背景与挑战
Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely.
系统核心：自动模式发现
We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval.
系统机制
核心机制包含以下三个层面：
- A closed-world field catalog constrains LLM-based schema discovery to attested fields
- deterministic structural analysis infers identity keys, foreign keys, and source hierarchy
- the resulting schema drives extraction, deduplication, and cross-source linking into a provenance-aware knowledge graph
At query time the schema -- optionally extended via a monotonic protocol -- conditions a multi-tool agent routing retrieval across structured lookup, graph traversal, and vector search, returning grounded answers with traceable citations.
实验与评估结果
In controlled zero-shot comparisons using the same LLM, data, and evaluation harness, the system improves over retrieval-only and decomposition-based baselines across four QA benchmarks, with ablations showing that schema-conditioned routing, structural intelligence, and schema-guided construction each contribute to the gains.