II · Planning & Control FlowEmerging★

Strategic Preparation Phase

also known as Problem-Space Mapping, Mental Model Build Phase

Mandate an explicit problem-space representation step before the agent attempts solutions, mirroring how expert humans build a mental model of constraints and dependencies before solving.

Context

An agent receives a complex request with interconnected constraints — schedule that depends on this and conflicts with that. The default LLM behavior is premature-closure: produce a fluent answer immediately, optimized for sounding right rather than holding the constraint web in mind.

Problem

Without a forced preparation step, the agent commits early to a path that ignores cross-constraint interactions. By the time errors surface, the plan has compounded. Cognitive-science research (Newell & Simon 1972, Langley & Simon 1987) shows expert human problem-solvers explicitly spend disproportionate time on preparation before attempting solutions; the agent is structurally biased the opposite way.

Forces

  • Preparation adds latency before any visible progress.
  • On easy tasks the preparation step is dead weight.
  • The preparation artifact must be usable by the planner — not just produced and discarded.

Example

A crossword-solving agent given a 6x6 puzzle. Naive LLM fills cells in clue order and gets five intersections wrong. With Strategic Preparation: first step is 'Mapping out the crossword puzzle clues, listing both the across and down entries, and determining the letter count for each.' Only after producing this map does the agent attempt solutions. Result: nearly perfect solution in 2 minutes vs five errors in seconds.

Diagram

Solution

Therefore:

Add a Preparation node to the agent's pipeline: given the goal, produce a structured problem-space representation as the first step. The artifact lists explicit constraints, dependency graph, declared success criteria, known unknowns. The planner is required to read and cite the artifact. Triggered by problem complexity heuristics so easy tasks skip it. Pair with generate-and-test-strategy (uses the artifact to test candidates), decision-context-maps (gather inputs into the artifact), planner-executor-verifier.

What this pattern forbids. The planner may not generate a plan without producing and citing a preparation artifact; complexity-gating may skip the artifact for trivial tasks, but the gate itself must be explicit.

And the patterns that stand alongside it, or against it —

  • complementsDecision Context Maps★— Before any consequential decision, require the agent to gather a declared set of contextual inputs (resource availability, schedules, downstream dependencies) into a 'context map' the decision must cite.
  • complementsGenerate-and-Test Strategy★— Generate multiple candidate solutions in parallel, then systematically test each against declared constraints rather than committing to the first plausible one — adapted from Langley & Simon's cognitive-science research on human expert problem-solving.
  • complementsPlanner-Executor-Verifier (PEV)★— Triadic specialization where a planner produces the plan, an executor runs it, and a separate verifier checks each step's effects against the original goal.
  • alternative-toPremature Closure✕— The LLM commits to a confident answer before processing all constraints, characteristic of constraint-heavy tasks where it fills in plausible answers fast and gets cross-constraint interactions wrong.
  • complementsPre-Flight Spec Authoring★— Before any code is generated, author a multi-pillar spec and have the agent critique it for ambiguity and edge cases, so that the loop executes against a reviewed target rather than a fresh prompt.
  • alternative-toContext Fragmentation✕— Anti-pattern: the LLM cannot hold multiple interconnected constraints in mind simultaneously the way human working memory can; it processes each constraint locally and loses the cross-constraint view.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

References

Provenance