---
title: "Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.41172v1"
permalink: "https://feed.astralor.com/items/itm_1986010330cd6e1b54e2f9b6"
published: "2026-10-30T02:48:37.000Z"
score: 58
channel: "tech"
tags: ["LLM","AI Agent","开源","推理效率","RAG","Context","Infrastructure","Knowledge Compilation"]
---

# Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses

## 速览

Retrieval-augmented generation is becoming agentic. A search harness writes queries, reads results, reformulates, and decides when to stop. This largely solves accuracy: a harness with only BM25/grep and MiniMax M3 answ…

## 关键点

- Retrieval-augmented generation is becoming agentic.
- A search harness writes queries, reads results, reformulates, and decides when to stop.
- This largely solves accuracy: a harness with only BM25/grep and MiniMax M3 answers 85% of BrowseComp-Plus and 91% on multi-hop FRAMES in our runs, without compiled or vector indexes.

## 全文

Retrieval-augmented generation is becoming agentic. A search harness writes queries, reads results, reformulates, and decides when to stop. This largely solves accuracy: a harness with only BM25/grep and MiniMax M3 answers 85% of BrowseComp-Plus and 91% on multi-hop FRAMES in our runs, without compiled or vector indexes. It exposes a context problem: an undisciplined loop repeats queries, rereads documents, and fills the window with unused passages. The missing layer is knowledge compilation: a configurable ingestion pipeline where LLMs enrich documents with context no chunk contains alone--navigation hierarchies with claim-evidence leaves, entity graphs, timelines, mind maps, ontologies, wikis, and memory. Compilation is not a better retriever: under a competent harness, structural artifacts gave no detectable accuracy gain on FRAMES, and a PageIndex-style outline degraded at scale. It is a supply layer. A navigation tree whose leaves are claim-evidence pairs--the mechanism we measure--cuts query tokens by 91% when evidence suffices and adds 1.9% when it does not, a 38% average reduction; this implies a 2% break-even sufficiency rate and a measured rate near 43%. A decision gate cuts latency from 140 s to 30 s, though substitution's token saving is bought with retrieval rounds and carries its own latency cost. Other artifacts--ontology, graph, wiki, timeline, mind map, memory--pay off in deployment (governance, integration, onboarding, temporal orientation, continuity) where accuracy benchmarks cannot see them. We describe RAGFlow's pipeline and harness (open source at https://github.com/infiniflow/ragflow), which turns the loop into five disciplined stations and keeps the context entering the model the smallest sufficient set; together they form an agent-native database: a store that hands the agent compiled, governed context instead of a ranked list of passages.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_1986010330cd6e1b54e2f9b6