Software World Models: From Consequence Prediction to Decision Value

Excerpt

arXiv:2610.04940v1 Announce Type: cross Abstract: A coding agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it. Exhaustively running integration tests after every agent action is impractical, so the agent must predict these failures before executing them. Existing software world models predict the agent's own observations, while static change-impact analysis only identifies where a change may propagate. We instead introdu