Metraipolis › archive › dc_84087e9a4e79

Reconfigurable Action Theories: A Formal Foundation for Dynamically Composable Agent Harnesses — arXiv:2611.12300

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12300
License (as archived)
CC0-1.0
Archived
2026-11-10T18:41:49.514Z
SHA-256 of the archived text
e34520962e3e43077984a6aeb437c5e7ce8af6d9c9ef23a5c3e9cd8049056d44
Stable URL of this page
https://metraipolis.com/documento/dc_84087e9a4e79

How to cite

Reconfigurable Action Theories: A Formal Foundation for Dynamically Composable Agent Harnesses — arXiv:2611.12300 — arXiv (en), https://arxiv.org/abs/2611.12300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84087e9a4e79 (Metraipolis archive dc_84087e9a4e79, sha256 e34520962e3e43077984a6aeb437c5e7ce8af6d9c9ef23a5c3e9cd8049056d44)
BibTeX
@misc{dc84087e9a4e79,
  title = {Reconfigurable Action Theories: A Formal Foundation for Dynamically Composable Agent Harnesses — arXiv:2611.12300},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12300},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84087e9a4e79; sha256 e34520962e3e43077984a6aeb437c5e7ce8af6d9c9ef23a5c3e9cd8049056d44},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Action theories typically fix their vocabulary and causal laws, whereas agent harnesses can change their tools, providers, and policies during execution. We introduce Reconfigurable Action Theories (RAT), in which actions can change the action theory itself. A theory module in RAT contains a vocabulary, causal laws, and an initializer. A RAT configuration records the active modules and the world state. Module loading and unloading are represented by actions governed by ordinary causal laws. RAT retains the standard causal action semantics of its language fragment when the active module set is fixed. We give sufficient conditions for at most one next configuration, preservation of existing behavior when a module is added, and equal results when modules are loaded in either order. We establish the computational complexity of reasoning tasks in RAT and translate finite RAT systems into nonmonotonic causal theories and Answer Set Programming (ASP), preserving bounded executions. Experiments compare finite RAT models with executions of official DeepSeek Harness, Pi, and OpenHands implementations. RAT provides a formal basis for checking how component changes affect a harness's available actions, behavior, and reachable goals.

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/2611.12300 — 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 2026-11-10T18:37:37.546Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).