Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents

Michael Nguyen, Wei Chen Tan, Nurul Aisyah Hassan +3

A growing body of work improves frozen large language models (LLMs) as agents by evolving their harness: the textual scaffolding around the model, including persona, strategy, form…