Metraipolis › archive › dc_2f350128fb1e

Active Inference as Context Acquisition for AI Agents — arXiv:2608.19202

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19202
License (as archived)
CC0-1.0
Archived
2026-10-18T11:39:24.848Z
SHA-256 of the archived text
0ff1a617059017c79f7bb15bd1dc900a058f9cdb6aab1f514889f8a2e40c252c
Stable URL of this page
https://metraipolis.com/documento/dc_2f350128fb1e

How to cite

Active Inference as Context Acquisition for AI Agents — arXiv:2608.19202 — arXiv (en), https://arxiv.org/abs/2608.19202 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f350128fb1e (Metraipolis archive dc_2f350128fb1e, sha256 0ff1a617059017c79f7bb15bd1dc900a058f9cdb6aab1f514889f8a2e40c252c)
BibTeX
@misc{dc2f350128fb1e,
  title = {Active Inference as Context Acquisition for AI Agents — arXiv:2608.19202},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19202},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f350128fb1e; sha256 0ff1a617059017c79f7bb15bd1dc900a058f9cdb6aab1f514889f8a2e40c252c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19202. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this tradeoff as active inference for context acquisition. An inner inference step updates beliefs over a latent task state, and an outer decision selects the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings, the epistemic term reduces to expected information gain, optionally normalized by token cost. We instantiate the framework in Optimal Question Asking (OQA), with exact posteriors and a dynamic programming oracle, and benchmark frontier language models on binary and multiway categorical tasks from 25 to 300 candidates. We also study clarification before generation and automated prompt optimization under token budgets. The formulation is model-agnostic and views active inference as a design principle for the context-acquisition layer of AI agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.19202 — 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 2026-10-18T11:38:27.937Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).