SOURCE-LINKED INTELLIGENCE

Safe Harness Self-Evolution: A Theoretical Analysis of Feasibility and Limits

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping the underlying language model frozen, with changes persisting across subsequent tasks. We provide a systematic theoretical analysis of the feasibility and limits of safe harness self-evolution, connecting modification generation, finite-data certification and selection, safe adoption, and behavior after an update. Under a fixed user-task distribution, we establish conditions guaranteeing overall expected-reward improvement while controlling chan

Read original source ↗ Open in workspace

recordType

paper

region

Global