Preprint
Sep 2026
Beyond the Model: Demystifying Harness Effects in Software Engineering Agents
Large Language Model (LLM)-based agents are increasingly used for software engineering tasks, yet their performance is not determined by the base model alone. The agent harness substantially shapes how SE agents interact with repositories, execute actions, and validate solutions. However, the role of harness design rem...
Hai-Chuan Hu, Quan-Jun Zhang, Sheng-Cheng Yu et al.
· 0 citations