liveBook · Manning

Proactive planning

As explained in Retrieval Augmented Generation, The Foundational Ideas

Proactive planning is a retrieval strategy that structures an information need and plans retrieval steps before initial retrieval.

Proactive planning structures an information need before retrieval begins. Instead of sending a complex question directly to one vector search, a high-level searcher decomposes it into atomic sub-queries, then coordinates retrieval and later verification. section 11.0

A plan-and-refine retrieval architecture typically:

  • Decomposes a multi-hop question into atomic sub-queries. section 11.0
  • Routes each sub-query to an appropriate search modality, such as sparse keyword search for entities or dense search for themes. section 11.0
  • Synthesizes the retrieved results, checks whether they answer the complete question, and creates supplementary plans when gaps remain. section 11.0

Comparing policies across documents

A question such as “Compare Policy A and Policy B” is treated as a multi-document research task rather than one undifferentiated search. The planner creates atomic searches, executes them through low-level searchers, and verifies that the combined evidence supports the comparison. section 11.4

Table 11.1 Strategic selection matrix
Feature
CRAG (Corrective)
LevelRAG (Plan-and-Refine)
Primary Mechanism
Evaluation & Fallback
Decomposition & Hierarchical Search
Best Use Case
Fact-Checking, Real-time Validation
Complex Research, Multi-document Synthesis
Key Innovation
Decompose-then-Recompose
High-Level Logic Planning
Compliance Role
Screening ("Is X a PEP?")
Advisory ("Compare Policy A vs B")
Latency Profile
Low (Internal) / High (Web Fallback)
High (Iterative Planning)
Architecture
Component Add-on
Full System Architecture

Use the strategic selection matrix to compare proactive planning with reactive correction across mechanism, use case, latency, compliance role, and architecture. section 11.4

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains decomposition, modality routing, synthesis, and verification, but does not specify planner implementation details.
Examples
Uses policy comparison, entity-focused sparse search, thematic dense search, and atomic sub-query execution as examples.
What it assumes
Assumes familiarity with retrieval pipelines, vector search, and multi-document questions.
What you can do after
Apply it via a LevelRAG-style architecture to decompose, route, execute, synthesize, and verify complex retrieval tasks.
How it connects
Connects multi-hop queries with vector search, heterogeneous retrieval, iterative verification, and CRAG correction loops.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.