SOURCE-LINKED INTELLIGENCE

Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Prompt-policy editing offers a practical way to improve agents that synthesize executable workflows without updating the underlying model. However, persistent prompt editing has two coupled properties. First, edit locality does not imply effect locality: an edit confined to one policy segment can ripple through downstream execution, altering behavior beyond the edited segment. Second, edit effects are composition-sensitive: edits that work in isolation can interfere after composition, causing one or both to lose their benefit or become harmful. Persistent adaptation must therefore support two

Read original source ↗ Open in workspace

recordType

paper

region

Global