Metraipolis › archive › dc_8ecbb77b120b

Agentic World Modeling for Agent Test-time Scaling without Environment Replica — arXiv:2610.40927

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40927
License (as archived)
CC0-1.0
Archived
2026-11-03T07:49:16.141Z
SHA-256 of the archived text
5f6b4632000eb5b76616d005a23211853cd2e7768a4c4f064a586f9e1ea257dd
Stable URL of this page
https://metraipolis.com/documento/dc_8ecbb77b120b

How to cite

Agentic World Modeling for Agent Test-time Scaling without Environment Replica — arXiv:2610.40927 — arXiv (en), https://arxiv.org/abs/2610.40927 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ecbb77b120b (Metraipolis archive dc_8ecbb77b120b, sha256 5f6b4632000eb5b76616d005a23211853cd2e7768a4c4f064a586f9e1ea257dd)
BibTeX
@misc{dc8ecbb77b120b,
  title = {Agentic World Modeling for Agent Test-time Scaling without Environment Replica — arXiv:2610.40927},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40927},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ecbb77b120b; sha256 5f6b4632000eb5b76616d005a23211853cd2e7768a4c4f064a586f9e1ea257dd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40927. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Test-time scaling (TTS) improves large language model agents by sampling and selecting among multiple candidate trajectories, but common realizations assume that these trajectories can be executed in parallel. This assumption breaks in realistic deployments, where enterprise workspaces and cloud services are shared and persistent, costly or infeasible to replicate, and actions may introduce irreversible side effects or cross-trajectory interference. Existing generative world models avoid direct execution, but typically compress environment state into a single prompt, limiting their ability to reliably simulate transitions under partial observability. Instead, we introduce Agentic World Modeling (AWM), which reformulates next-observation prediction as a multi-turn evidence-acquisition task. For each hypothetical action, an agentic simulator adaptively queries the real environment through safe read-only interfaces, reasons over the returned evidence, and uses executable computation to construct the resulting observation without mutating shared state. Integrated with trajectory-level TTS, AWM enables parallel exploration over a single shared environment. Across $\tau$-bench, AppWorld, and OfficeBench, AWM outperforms a single-shot simulation baseline by 40.07% on average, and surpasses a trained world-model baseline by 12.36% on average. These results establish interactive, read-grounded simulation as a practical foundation for safe and scalable agentic test-time scaling in shared, non-resettable environments.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.40927 — 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 2026-11-03T07:49:16.049Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).