# CTIFoundry：索引时构建结构提升智能体F1

- 来源：DAIR.AI (@dair_ai)
- 发布时间：2026-08-21 04:26
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmt1znys70cvproovlmtntcgg
- 原文链接：https://x.com/dair_ai/status/2090535851612942340

## AI 摘要

Amazon 团队提出 CTIFoundry，在索引时跨四个权威安全知识库构建官方交叉引用为类型化可遍历边，并通过 span 级报告层保留来源。仅替换动作表面，即在四模型面板上将相同 harness 的智能体整体 F1 提升 0.19-0.28；小模型在 CTIFoundry 上以约一半工具调用数超越旗舰模型在平面基座上的表现。

## 正文

Very interesting new work Amazon and colleagues.

(bookmark it)

This connects to the emerging theme of treating the corpus as part of the harness. Planning loops, tool protocols, and context management have matured fast, while the knowledge an agent investigates over still sits behind an embedding index as opaque chunks.

CTIFoundry builds structure at index time instead. Official cross-references across four authoritative security knowledge bases become typed traversable edges, and a span-grounded report layer keeps provenance attached to every chunk. Seven typed tools and three procedural skills expose that structure on a stock open-source harness.

Swapping only the action surface lifts the identically-harnessed agent by 0.19 to 0.28 overall F1 across a four-model panel. A small model on the scaffold beats a flagship on the flat substrate at roughly half the tool calls.

Paper: https://arxiv.org/abs/2608.18613

Track more trending AI papers in our academy: https://academy.dair.ai/