Metraipolis › archive › dc_083b111f5ecb

Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds — arXiv:2610.11552

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11552
License (as archived)
CC0-1.0
Archived
2026-10-09T05:48:02.207Z
SHA-256 of the archived text
5490c1f5e09fd2f8999e5d2c24e0ac6159aa14ddc5464072ddeb0e430bc54a6e
Stable URL of this page
https://metraipolis.com/documento/dc_083b111f5ecb

How to cite

Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds — arXiv:2610.11552 — arXiv (en), https://arxiv.org/abs/2610.11552 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_083b111f5ecb (Metraipolis archive dc_083b111f5ecb, sha256 5490c1f5e09fd2f8999e5d2c24e0ac6159aa14ddc5464072ddeb0e430bc54a6e)
BibTeX
@misc{dc083b111f5ecb,
  title = {Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds — arXiv:2610.11552},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11552},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_083b111f5ecb; sha256 5490c1f5e09fd2f8999e5d2c24e0ac6159aa14ddc5464072ddeb0e430bc54a6e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11552. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking across multiple records. To address these challenges, we introduce E-Ledger, a multi-agent harness for safe and persistent execution. E-Ledger employs a code approval layer that checks every proposed action against policy before execution, and maintains a world ledger of verified hidden rules alongside evidence-backed dynamic state. Because hidden rules are typically unknown a priori, we further propose WorldAbduct, an abductive, world-model-driven harness evolution framework. WorldAbduct diagnoses execution trajectories across four complementary views (state consistency, world-observation gap, policy-gate correctness, and goal judgment) to hypothesize latent rules, and verifies them through targeted abductive interactions before integrating them into the ledger. On the enterprise benchmark World of Workflows, E-Ledger with WorldAbduct improves safe task completion across four LLM backbones, outperforming the strongest evolution baseline by 5--15 percentage points. Experiments in ScienceWorld and DiscoveryWorld further show that abductive harness evolution carries over to scientific environments. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.11552 — 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 2026-10-09T05:47:00.801Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).