{"ID":2824170,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.23144","arxiv_id":"2512.23144","title":"An Inference-Based Architecture for Intent and Affordance Saturation in Decision-Making","abstract":"Decision paralysis, i.e. hesitation, freezing, or failure to act despite full knowledge and motivation, poses a challenge for choice models that assume options are already specified and readily comparable. Drawing on qualitative reports in autism research that are especially salient, we propose a computational account in which paralysis arises from convergence failure in a hierarchical decision process. We separate intent selection (what to pursue) from affordance selection (how to pursue the goal) and formalize commitment as inference under a mixture of reverse- and forward-Kullback-Leibler (KL) objectives. Reverse KL is mode-seeking and promotes rapid commitment, whereas forward KL is mode-covering and preserves multiple plausible goals or actions. In static and dynamic (drift-diffusion) models, forward-KL-biased inference yields slow, heavy-tailed response times and two distinct failure modes, intent saturation and affordance saturation, when values are similar. Simulations in multi-option tasks reproduce key features of decision inertia and shutdown, treating autism as an extreme regime of a general, inference-based, decision-making continuum.","short_abstract":"Decision paralysis, i.e. hesitation, freezing, or failure to act despite full knowledge and motivation, poses a challenge for choice models that assume options are already specified and readily comparable. Drawing on qualitative reports in autism research that are especially salient, we propose a computational account...","url_abs":"https://arxiv.org/abs/2512.23144","url_pdf":"https://arxiv.org/pdf/2512.23144v1","authors":"[\"Wendyam Eric Lionel Ilboudo\",\"Saori C Tanaka\"]","published":"2025-12-29T02:13:34Z","proceeding":"q-bio.NC","tasks":"[\"q-bio.NC\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}