AI RESEARCH
It's Not the Size: Harness Design Determines Operational Stability in Small Language Models
arXiv CS.AI
•
ArXi:2605.12129v1 Announce Type: cross This paper experimentally analyzes how the level of harness engineering affects the operational performance of small language models (SLMs, 2-3B parameters). Three harness conditions - model-only (raw prompt), minimal-shell (wrapper