Jul 2026
Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents
Self-improving agents accumulate capability by repeatedly rewriting procedural policies, controllers, or heuristic rules. They typically rely on self-authored tests or metrics to decide whether to accept subsequent edits. The agent controls both the optimized object and its verifier. As a result, self-assigned scores c...
Diandian Guo, Cong Cao, Fangfang Yuan et al.
· arXiv.org · 0 citations