I · ReasoningEmerging★

Large Reasoning Model (LRM) Paradigm

also known as LRM, Reasoning-Tuned Model, Inference-Time Reasoning

Route reasoning-heavy tasks to a reasoning-tuned model that trades inference time for deliberation, rather than to a fast LLM that exhibits premature-closure.

Context

A task involves interconnected constraints, multi-step deduction, math, or formal reasoning. Standard LLMs (GPT-4o-class) respond fast but make systematic errors on constraint-heavy problems because next-token prediction biases toward fluency over correctness. Reasoning-tuned models exist (o1 family, DeepSeek R1, Gemini Thinking) — slow but methodical.

Problem

Routing every task to a fast LLM means constraint-heavy tasks fail in characteristic ways (premature-closure, false-confidence-syndrome). Routing everything to an LRM is slow and expensive for easy tasks. The team needs a routing decision.

Forces

  • LRM latency is 10–100× LLM (often minutes).
  • LRM cost is higher per token.
  • Some tasks genuinely need fast response; LRM is unacceptable there.

Example

A financial-analysis agent handles two query types: 'what was Apple's Q3 revenue' (simple lookup) and 'given these 12 covenants, can this acquisition close?' (multi-constraint reasoning). Router sends the first to GPT-4o-mini (200ms, $0.0001). Second goes to o1 (90s, $0.40, methodically tests each covenant against the term sheet). Both succeed at their task class; routing keeps cost bounded.

Diagram

Solution

Therefore:

Build a router that classifies tasks: simple lookups / generation → LLM; multi-step math, formal reasoning, interconnected-constraint problems → LRM. Track per-class success rate to refine routing. Pair with complexity-based-routing, multi-model-routing, test-time-compute-scaling, generate-and-test-strategy, golden-rule-simpler-is-better (don't overuse LRM).

What this pattern forbids. LRM is used only for tasks classified as constraint-heavy / multi-step-reasoning; routing decisions are logged and reviewed.

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

  • complementsComplexity-Based Routing★— Estimate a request's difficulty up front and bind it to the cheapest model tier that can answer well, using an explicit complexity classifier as the routing key.
  • complementsMulti-Model Routing★★— Send each request to the cheapest model that can handle it well.
  • complementsTest-Time Compute Scaling★★— Allocate more inference-time compute (samples, search, deeper thinking) instead of scaling parameters to improve quality.
  • complementsExtended Thinking★★— Spend a configurable budget of internal reasoning tokens before producing a user-visible answer.
  • 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.
  • 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.
  • 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.
  • complementsTest-Time Memorization (Titans)·— Memory module that learns at inference time by incorporating recent inputs into its parameters during the session rather than relying solely on pre-trained weights.
  • complementsDeliberation Over Observation✕— Anti-pattern: give a reasoning-trained model a large thinking budget in an interactive environment and it hypothesises about the environment's state instead of issuing the cheap observation that would settle it.

Neighbourhood

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

Used in frameworks

References

Provenance