arXiv cs.CL· Zhichang Yu, Baining Cao, Sbaaoui Idriss, Qi Wang, Gangqiang Xu, Ling Qin, Xiaoling Jin, An Liu, Shaohao Cai, Xiaoyang Bao, Shengle Chen, Changchang Ding, Pengfei Zhu, Jingxiang Xu, Yifeng Mao, Lu Liu, Hai Jin, Yingfeng Zhang·· 11 小时前AI 评分55
Context as Infrastructure：面向智能体系统检索的知识编译与 harness
Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses
AI 导读
论文提出把知识编译作为智能体检索的上下文供给层，用 LLM 在入库阶段为文档补充导航层级、实体图、时间线等结构。
正文 · 原文
Authors:Zhichang Yu, Baining Cao, Sbaaoui Idriss, Qi Wang, Gangqiang Xu, Ling Qin, Xiaoling Jin, An Liu, Shaohao Cai, Xiaoyang Bao, Shengle Chen, Changchang Ding, Pengfei Zhu, Jingxiang Xu, Yifeng Mao, Lu Liu, Hai Jin, Yingfeng Zhang
Abstract: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 this https URL), 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.
| Comments: | 13 pages, 2 figures |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.41172 [cs.IR] |
| (or arXiv:2610.41172v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41172 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yingfeng Zhang [view email]
[v1]
Fri, 30 Oct 2026 02:48:37 UTC (32 KB)
来源：arXiv cs.CL · arxiv.org