Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data· 通过自适应结构化提高数据推理效率
Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI is deploying LLM agents that reason over this data to answer complex questions for every knowledge worker. Agents can do this today, but at prohibitive cost. Each question repeatedly opens large documents to recover scattered evidence, consuming up to a million tokens. However, if the data were already structured, the same question would reduce to a cheap database lookup. For example, on FanOutQA benchmark, reasoning over an ideal pre-structured store is 28X cheaper, and the gap grows to orders of magnitude as questions fan out over more documents. Yet structuring everything in advance is not viable: documents hold vastly more possible struc
通过自适应结构化提高数据推理效率，降低 LLM 代理成本。
- 核心方法
- 提出一种自适应结构化方法，将无结构数据转换为预结构化存储，从而减少推理所需的 token 数量。
- 适合谁读
- 研究者、工程师、产品经理
- 要解决的问题
- 当前 LLM 代理在处理无结构数据时成本高昂，需要大量 token 来恢复分散的证据。
- 关键实验
- 实验在 FanOutQA 基准上进行，展示了自适应结构化方法的成本效益。
- 主要贡献
- 在 FanOutQA 基准上展示了 28 倍的成本减少，为复杂文档查询提供了更经济有效的解决方案。
- 意义与局限
- 该方法可显著降低企业 AI 中 LLM 代理的使用成本，但全面预结构化所有文档在实际操作中仍面临挑战。