Metraipolis › archive › dc_c7448d837ada

Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality — arXiv:2609.02242

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02242
License (as archived)
CC0-1.0
Archived
2026-10-17T03:24:16.933Z
SHA-256 of the archived text
71abe02ffd52525fd2bd2f20d53759aa2a47467c188394bd793b460d70932173
Stable URL of this page
https://metraipolis.com/documento/dc_c7448d837ada

How to cite

Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality — arXiv:2609.02242 — arXiv (en), https://arxiv.org/abs/2609.02242 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7448d837ada (Metraipolis archive dc_c7448d837ada, sha256 71abe02ffd52525fd2bd2f20d53759aa2a47467c188394bd793b460d70932173)
BibTeX
@misc{dcc7448d837ada,
  title = {Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality — arXiv:2609.02242},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02242},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7448d837ada; sha256 71abe02ffd52525fd2bd2f20d53759aa2a47467c188394bd793b460d70932173},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02242. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI assistants often collaborate by proposing candidate edits, plans, or designs that users evaluate before adoption. Existing assistance methods focus on proposal quality or user-goal inference, often assuming that the user can reliably evaluate any proposal, which can fail in practice because of bounded rationality. We study evaluability-aware proposal planning, where proposals serve both as task interventions and as probes for learning latent preferences and evaluation constraints, where the resulting belief updates then guide later proposals. We formalise this setting as ProSE, a hidden-parameter sequential assistance problem, and instantiate it with a KL-regularised bounded-rational binary response model in which acceptance trades off value gain against a distance-dependent evaluability penalty. Analysing the planning consequence of this likelihood reveals that likely accepted proposals and informative probes need not coincide, which explains why planners that only pursue acceptance systematically underperform. We operationalise ProSE with \textsc{ProSE-Plan}, a depth-2 Bayes-adaptive planner that scores proposals by possible responses and response-induced posterior beliefs. In controlled graph simulations, \textsc{ProSE-Plan} improves over evaluability-unaware and myopic baselines when evaluation cost is the bottleneck, and a probe-commit ablation confirms that our approach selects informative proposals that simpler methods miss. Our results thus identify user evaluability as a planning-relevant dimension of AI assistance, complementary to generation quality and preference inference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.02242 — 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 2026-10-17T03:12:51.781Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).