SOURCE-LINKED INTELLIGENCE

Making Agents More Consistent: Skills Should Form Habits for Repeat Tasks

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

On repeated work, agents are inconsistent. We ran 42 tasks three times each and found that, depending on the model, 38% to 74% returned answers that did not agree. Consistency is what a buyer, an auditor, or a regulator requires, and agents do not have it. They are wasteful too: 95.3% to 97.2% of what an agent generates goes to re-deriving a plan the system already knows. We propose skill habit formation. An agent mines its own execution history for candidate skills, deterministic variants that compete against the incumbent rather than replacing it. A candidate declares the region of input spa

Read original source ↗ Open in workspace

recordType

paper

region

Global