Metraipolis › archive › dc_50904bfe3ee9

Software World Models: From Consequence Prediction to Decision Value — arXiv:2610.04940

Source
arXiv
Original
https://arxiv.org/abs/2610.04940
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:34.718Z
SHA-256 of the archived text
c3cfe33c6216b614b3f93b4999bbc03a9e2c2232f9596b87e9ae142deb42dc15
Stable URL of this page
https://metraipolis.com/documento/dc_50904bfe3ee9

How to cite

Software World Models: From Consequence Prediction to Decision Value — arXiv:2610.04940 — arXiv, https://arxiv.org/abs/2610.04940 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50904bfe3ee9 (Metraipolis archive dc_50904bfe3ee9, sha256 c3cfe33c6216b614b3f93b4999bbc03a9e2c2232f9596b87e9ae142deb42dc15)
BibTeX
@misc{dc50904bfe3ee9,
  title = {Software World Models: From Consequence Prediction to Decision Value — arXiv:2610.04940},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04940},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50904bfe3ee9; sha256 c3cfe33c6216b614b3f93b4999bbc03a9e2c2232f9596b87e9ae142deb42dc15},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04940. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 introduce the Software World Model (SWM), which models the broader system affected by a code change and predicts its blast set: the components that the change will break. SWM follows three stages: explore, learn, and act. Explore executes candidate changes from restored system states, prioritizing regions where observed failures contradict the dependency graph. Learn fine-tunes a language model on these execution outcomes to predict downstream breakage. Act converts sampled predictions into per-consumer break probabilities for change ranking, proactive migration, and deciding when another execution is worth its cost. On held-out synthetic systems, SWM improves blast-set F1 from 0.431 for static reachability to $0.571\pm0.037$, more than halves ranking regret, and improves migration return at all nine evaluation checkpoints. The two methods are complementary: reachability is stronger on dependencies represented in the graph, while SWM recovers failures caused by couplings the graph misses. Experiments on held-out real libraries further show that predicting structured failure outcomes, rather than only scalar risk, is important for downstream decision quality.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.04940 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.944Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).