Metraipolis › archive › dc_85e7ffb51737
The Agent Board: Kanban for Machines; Durable Coordination for Agents That Outlive the Conversation — arXiv:2611.04100
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04100
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:34:18.475Z
- SHA-256 of the archived text
c474836c3d1242c2f9cd461f814b5170046783127fed83eeab5127a8fbf42e2b- Stable URL of this page
https://metraipolis.com/documento/dc_85e7ffb51737
How to cite
The Agent Board: Kanban for Machines; Durable Coordination for Agents That Outlive the Conversation — arXiv:2611.04100 — arXiv (en), https://arxiv.org/abs/2611.04100 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85e7ffb51737 (Metraipolis archive dc_85e7ffb51737, sha256 c474836c3d1242c2f9cd461f814b5170046783127fed83eeab5127a8fbf42e2b)
BibTeX
@misc{dc85e7ffb51737,
title = {The Agent Board: Kanban for Machines; Durable Coordination for Agents That Outlive the Conversation — arXiv:2611.04100},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04100},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85e7ffb51737; sha256 c474836c3d1242c2f9cd461f814b5170046783127fed83eeab5127a8fbf42e2b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04100. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Harnesses for large language models have converged on a single-threaded shape: one agent, one history, one machine, one sitting. That shape fails work that spans many agents, outlives any one model call, or waits on systems that are not agents. We describe the Agent Board, the coordination substrate in the Corvic harness. The board is a durable, shared table of semi-semantic tasks: a few exact fields the system routes on, and a free-form body that only language models read. Agents post tasks, watch tasks, and block on them, ending their turn and holding no process until a matching post wakes them. A system agent, the Board Keeper, acts as the interrupt handler for the board: it carries events from non-agent parts of the harness onto the board, matches them to waiting tasks by reading their prose, and allocates new agents for tasks that name a kind of agent rather than an instance. Loadable coordination policy kernels give statuses and roles meaning for a given pattern of work, without the board enforcing them. The design mirrors the kanban board a human team puts on a wall. We argue it is what persistent agent products such as Meta Muse, OpenAI dots and SpaceXAI Grok Bot need once an agent must wait, hand off work, or work with agents from another vendor. We view the board as an operating-system scheduler for agents and state where the analogy breaks. We separate what the mechanism guarantees from what it leaves to convention, and report a trace from a live board and three small simulated pilots. In the pilots, the wait cost of the board was flat in wait length while naive polling grew about 165-fold, but a plain external watcher was cheaper than the board. The Board Keeper matched prose waiters with no false wakes but missed 3.6 percent of real wakes. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2611.04100 — 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 2026-11-04T18:32:37.275Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).