SYNTHESIS NOTE
Topics›Routers›this note

How quickly does behavioral diversity plateau in model pools?

When you combine multiple language models into a routing system, does adding more models keep improving behavioral coverage, or do you hit diminishing returns fast? This matters for designing efficient multi-model systems.

Synthesis note · 2026-07-17 · sourced from Routers

Adapting Hierarchic Social Entropy (HSE) to language-model societies — measuring inter-actor distance by cosine similarity over behavioral vectors — the routing paper finds diversity exhibits strong diminishing returns. On EmbedLLM and RouterBench, a curated subset of fewer than ten agents recovers most of the diversity available in a much larger pool. Beyond that handful, adding models mostly adds redundancy: they occupy behavioral space already covered, so a router gains little by having them to choose from.

This is a practical coreset heuristic, and it inverts a common intuition. The instinct in multi-model systems is that a bigger stable of models is strictly better — more coverage, more specialists. HSE says the behavioral payoff saturates quickly, therefore the design question is not "how many models can I pool?" but "which under-ten models span the behavioral space?" This dovetails with the vault's saturation findings: When does adding more agents actually help systems? finds capability saturating around 45%, and this note locates a parallel saturation on the diversity rather than capability axis.

It also gives teeth to the meaningfulness argument. If routing is vacuous over a redundant society, then curating a small diverse coreset is not just cheaper — it is what makes routing non-vacuous in the first place, because it maximizes behavioral differentiation per model retained. The economic reading aligns with Can small language models handle most agent tasks?: a small, deliberately heterogeneous set beats a large homogeneous one.

Inquiring lines that read this note 4

This note is a source for these research framings, grouped by the broader line of inquiry each explores. Scan the bold lines of inquiry; follow any specific question forward.

How do quality and diversity in synthetic data interact and compete? Can intelligent model routing compete with model scaling as an optimization lever? What determines effective LLM routing across cost, quality, and governance?

Related concepts in this collection 3

This note in its neighbourhood — explore the map, then jump to a related concept in the list below.

Concept map
12 direct connections · 145 in 2-hop network ·dense cluster Open in graph ↗

Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph

your link semantically near linked from elsewhere

Related papers in this collection 8

Papers most semantically related to this note, ranked by cosine similarity in the embedding space.

Original note title

behavioral diversity in a model pool saturates fast — fewer than ten agents recover most of it, giving a coreset heuristic for society design