Loop & Harness EngineeringChuyang Wei et al.
Self-Evolving Agent Harness released
Self-Evolving Agent Harness released — formalizes harness self-evolution, which revises prompts, memory, workflows and executable components while model weights stay fixed, and analyzes its reliability with evolutionary search and continual PAC learning
Why it matters
Under explicit assumptions it gives an expected generalization bound, a retention bound conditional on historical regression budgets, and a high-probability rule for admitting revisions using fresh independent data. It concludes that real deployment needs independent safeguards for learning, runtime privileges and consequential actions
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2610.18813Added in Week 42, 2026 · See that week