Fetching from the wire…
Agents2026-07-13 · source-backed
This paper introduces Hierarchic Social Entropy to measure behavioral differentiation among models and finds strong diminishing returns: a curated subset under ten agents recovers most available diversity (arXiv:2607.09197). It also found KNN routers gain accuracy with specialist models but collapse under perturbation, while prompted routing stays stable. The caution for builders fanning out swarms: high task accuracy doesn't guarantee robust routing, and past ~10 distinct agents you're adding cost without adding real behavioral coverage.
Each link below shares sources, entities, or timing with this story.
Shared entity: Fewer / Shared topic / Earlier coverage
Both cover Fewer; overlapping topics (agent, builder, cost); earlier Fewer coverage from 2026-05-18.
Same source domain / Shared topic / Downstream implication
Reported by the same outlet (arxiv.org); overlapping topics (builder, collapse, diversity); traces where this leads (implication).
Same source domain / Shared topic
Reported by the same outlet (arxiv.org); overlapping topics (accuracy, agent, builder, model).
Reported by the same outlet (arxiv.org); overlapping topics (adding, agent, cost, model).
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (agent, model); pushes against this story (against).
Reported by the same outlet (arxiv.org); overlapping topics (agent, cost); pushes against this story (versus).
Reported by the same outlet (arxiv.org); overlapping topics (cost, model); pushes against this story (against).
Same source domain / Shared topic / Downstream implication
Reported by the same outlet (arxiv.org); overlapping topics (agent, model); traces where this leads (implication).