Metraipolis › archive › dc_c53144fdf70c

Org-Agent: Beyond Personal Assistants Towards Organizational Agents — arXiv:2609.34392

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34392
License (as archived)
CC0-1.0
Archived
2026-10-07T20:57:43.889Z
SHA-256 of the archived text
7ec34dc76aa9913ef1cc0e44df1e8265750123cd05aaa9d61af276f56e1cc901
Stable URL of this page
https://metraipolis.com/documento/dc_c53144fdf70c

How to cite

Org-Agent: Beyond Personal Assistants Towards Organizational Agents — arXiv:2609.34392 — arXiv (en), https://arxiv.org/abs/2609.34392 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c53144fdf70c (Metraipolis archive dc_c53144fdf70c, sha256 7ec34dc76aa9913ef1cc0e44df1e8265750123cd05aaa9d61af276f56e1cc901)
BibTeX
@misc{dcc53144fdf70c,
  title = {Org-Agent: Beyond Personal Assistants Towards Organizational Agents — arXiv:2609.34392},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34392},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c53144fdf70c; sha256 7ec34dc76aa9913ef1cc0e44df1e8265750123cd05aaa9d61af276f56e1cc901},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34392. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language model agents serving organizations must coordinate requests from multiple users while using knowledge distributed across their interactions. We identify two complementary capabilities for this setting, namely cross-user interaction and decision-making, as well as cross-user memory and knowledge use. Both capabilities are governed by organizational constraints across three aspects: user identity, authority, and access permissions; the attribution and temporal validity of information; and rules for resolving conflicting requirements across users and completion requirements for joint decisions. These constraints shape what information or decisions must be obtained before an action can proceed and what conditions must be satisfied during its execution. Motivated by this, we introduce Org-Agent, a unified constraint-centric reasoning framework that organizes task execution in three stages. Specifically, Org-Agent decomposes a task into atomic subtasks and constructs a task dependency graph whose edges encode the dependencies among them. Building on this graph, it schedules the subtasks in dependency order through topological sorting. It then executes each subtask while accounting for the task's constraints, supported by evidence-acquisition and memory-management tools. Experiments on MUSES-Bench and GroupMemBench demonstrate the effectiveness of Org-Agent on both capabilities, and ablations further support the contributions of dependency modeling and tool use.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34392 — 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 2026-10-07T20:29:01.538Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).