Metraipolis › archive › dc_cd17c9bc9bbb

REALM: Identifying Minimal Task Assets for LLM Agents — arXiv:2610.39155

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39155
License (as archived): CC0-1.0
Archived: 2026-10-31T06:13:07.238Z
SHA-256 of the archived text: b8e827008d85374bac872c2f28a80aeda86d8f63eb9de28bc02dd1232787a5aa
Stable URL of this page: https://metraipolis.com/documento/dc_cd17c9bc9bbb

How to cite

REALM: Identifying Minimal Task Assets for LLM Agents — arXiv:2610.39155 — arXiv (en), https://arxiv.org/abs/2610.39155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd17c9bc9bbb (Metraipolis archive dc_cd17c9bc9bbb, sha256 b8e827008d85374bac872c2f28a80aeda86d8f63eb9de28bc02dd1232787a5aa)

BibTeX

@misc{dccd17c9bc9bbb,
  title = {REALM: Identifying Minimal Task Assets for LLM Agents — arXiv:2610.39155},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39155},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd17c9bc9bbb; sha256 b8e827008d85374bac872c2f28a80aeda86d8f63eb9de28bc02dd1232787a5aa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution toward unrelated resources. Applying least privilege therefore requires identifying the assets needed by a task, including assets whose identities emerge only during execution. We present REALM (Required Execution Assets Linked to a Mission), an approach to identifying and maintaining a task's required assets and their permitted uses. The approach represents required assets as Dependency Graph nodes, resolves prerequisite relationships, and admits newly discovered assets through source-scoped selection. It separates discovering an asset from authorizing its use, while preserving the agent's freedom to choose its computation. The REALM Builder maintains the selected grants and projects Asset Files; the Partial API Manager exposes resource-bound Partial APIs to the Agent inside a Task Container. Across 60 clean tasks and 560 injected cases in AgentDyn, it completes 40.0% and 36.4% of tasks and decreases ASR from 16.6% to 0.2% with qwen3.5-flash as the base model.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.39155 — 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 2026-10-31T06:07:08.701Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).