SOURCE-LINKED INTELLIGENCE

EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve capability, but a successful mutation may leave persistent effects that cannot be safely reversed in states different from the one in which it was created. We introduce EvoUndo, a framework for representing, synthesizing, diagnosing, and independently verifying recoverability of model-generated self-modifications across counterfactual states. Across 600 unseen one-shot self-evolution tasks, we identify 197 capability-improving mutations that fail r

Read original source ↗ Open in workspace

recordType

paper

region

Global