---
title: "ezo labs research"
updated: "2026-10-30"
type: CollectionPage
---

# ezo labs research

topics: inference (0), [environments](https://ezolabs.io/research/topic/environments.md) (2), [evals](https://ezolabs.io/research/topic/evals.md) (1). feed: [atom](https://ezolabs.io/research/atom.xml).

## [How many subagents is too many? We gave ours 12 slots; the median used 1.3.](https://ezolabs.io/research/agent-fleet-occupancy.md)

EZO-R-2026-03 // environments // 2026-10-30

**Slots waited on work.** Allowed 12 workers at once, the typical build kept about 1.3 busy (1.31 over 47 builds). In the six biggest, new work came 8 to 12 times too slowly to fill them.

html at [/research/agent-fleet-occupancy](https://ezolabs.io/research/agent-fleet-occupancy).

## [Let your lead agent only plan: fewer turns, same score](https://ezolabs.io/research/planner-only-swarms.md)

EZO-R-2026-02 // environments // 2026-10-30

**Fewer turns, same score.** In three paired runs of one task, a lead agent that only plans took 9 turns instead of 17 and compacted 4 times, not 5. All 168 tests passed. Total tokens did not fall.

html at [/research/planner-only-swarms](https://ezolabs.io/research/planner-only-swarms).

## [Your agent mostly sees one line of each skill. Write that line well.](https://ezolabs.io/research/skill-descriptions.md)

EZO-R-2026-05 // evals // 2026-10-30

**Mostly the description.** For diagrams and math, most answers came without the model opening the skill. Graphs and molecules usually came after it read the full page, which our rewrite also changed.

html at [/research/skill-descriptions](https://ezolabs.io/research/skill-descriptions).