将搜索与推理解耦：面向 LLM 智能体的厂商无关搜索接地架构 DSG

View PDF HTML (experimental)

Abstract:Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency, and generation behavior behind a single model-provider boundary. This coupling makes grounding hard to inspect, tune, reuse, or port, and can trigger Search-Induced Verbosity that breaks strict output contracts. We present Decoupled Search Grounding (DSG), a vendor-agnostic boundary that moves grounding outside the reasoning model through an MCP-compatible gateway, exposing provider routing, source-aware context rendering, configured fallback, retrieval-depth control, and exact plus semantic caching as first-class controls. Across five frontier models on SimpleQA, FreshQA, and HotpotQA, native search leads on recency-sensitive FreshQA, but DSG exposes a stronger frontier when control matters: on SimpleQA it nearly matches native accuracy (86.1% vs. 87.7%) at 91% lower search cost, preserves concise answer contracts, and reaches a 99.4% warm-cache hit rate with 68% lower latency. Deployed as a shared production grounding layer for large-scale agentic workloads with interchangeable models, DSG matches native-search accuracy on an e-commerce query-understanding (QIU) workload while cutting search cost by over 98%. Real-time grounding is best treated as an optimizable interface boundary, not a fixed model feature.

Comments:	Accepted at the EMNLP 2026; 16 pages, 9 figure
Subjects:	Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR); Multiagent Systems (cs.MA)
Cite as:	arXiv:2606.18947 [cs.AI]
	(or arXiv:2606.18947v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2606.18947 arXiv-issued DOI via DataCite

Submission history

From: Emmanuel Aboah Boateng [view email]
[v1] Wed, 17 Jun 2026 11:30:39 UTC (2,155 KB)
[v2] Sun, 11 Oct 2026 06:58:14 UTC (2,206 KB)