Metraipolis › archive › dc_9dbef2045f96

Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection — arXiv:2608.05085

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.05085
License (as archived): CC0-1.0
Archived: 2026-10-31T11:15:21.608Z
SHA-256 of the archived text: 900ebe1d11e4244c35a9443e2a00ee409275f92b397cb78208f156cda458ed60
Stable URL of this page: https://metraipolis.com/documento/dc_9dbef2045f96

How to cite

Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection — arXiv:2608.05085 — arXiv (en), https://arxiv.org/abs/2608.05085 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9dbef2045f96 (Metraipolis archive dc_9dbef2045f96, sha256 900ebe1d11e4244c35a9443e2a00ee409275f92b397cb78208f156cda458ed60)

BibTeX

@misc{dc9dbef2045f96,
  title = {Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection — arXiv:2608.05085},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05085},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9dbef2045f96; sha256 900ebe1d11e4244c35a9443e2a00ee409275f92b397cb78208f156cda458ed60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05085. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop. Many systems make these decisions by maximizing a myopic score such as expected information gain per unit cost or a learned plausibility score. We identify a structural limitation of this approach. Some actions are constructive: they acquire an epistemic capability (an instrument, assay, pipeline, simulator, or abstraction) whose value lies not in the information returned immediately but in the future actions it makes available. When the least-cost route to a confident answer requires a chain of such constructions, a planner that scores actions only by information obtainable within a bounded horizon cannot value the first construction: it yields no information within the horizon and is dominated by any measurement with positive information, however small. We formulate goal-directed discovery as a stochastic shortest-path problem in belief space in which constructive experiments change the downstream action graph, and prove that for every lookahead depth d there is an instance on which every myopic information-maximizing planner has an unbounded approximation ratio, and a related instance on which it never reaches the goal. The mechanism is a capability-indistinguishability lemma: within the horizon, acquiring a capability can be observationally indistinguishable from paying for a null action. This establishes capability gating as a reachability axis of difficulty distinct from curvature (submodularity) and information order (adaptivity gaps). We introduce CG-Plan, an incremental replanner with a capability-aware cost-to-go heuristic h = h_cap + h_exp. In a controlled testbed, the performance gap appears only under gating, persists for every fixed horizon, and arises when near-miss hypotheses come from a data-consistent proposer.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.05085 — 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 2026-10-31T11:02:13.575Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).