arXiv cs.AI· St John Grimbly, Nicolas Kuske, Evert A. Boonstra, Charel van Hoof, Rowan Hodson, Benjamin Rosman, Ryan Smith, Mark Solms, Jonathan P. Shock·· 3 天前AI 评分18
主动推理中内感受优先化的两条路径：解离似然精度与偏好重加权
Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference
AI 导读
研究在含三种致命需求的觅食网格世界中对比主动推理智能体的两种内感受优先化干预：提高精度可锐化内感受后验并提升存活率，偏好重加权则使身体状态远离致命边界并改变学习状态。在72个额外布局上的实验未能证实偏好重加权在困难布局上的预期收益，但两种干预均提升平均存活率且交互为正。仅凭存活率无法完整刻画模型如何优先化需求并学习身体模型。
正文 · 原文
Abstract:An embodied agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of information about that need or by increasing its preference for outcomes that relieve it. We compare these two interventions, separately and together, in a foraging gridworld with three lethal needs, and ask how each changes survival, perception and the body model the agent learns. Precision sharpens interoceptive posteriors and improves survival. Preference reweighting keeps bodily states further from their lethal boundaries and changes the states from which the agent learns, so its learned model covers fewer need levels, with lower quality across all levels but slightly higher quality on the levels it visits. An experiment on 72 further layouts does not establish the predicted preference benefit on difficult layouts, but both interventions improve average survival there and their interaction is positive. Survival alone therefore gives an incomplete account of how a model prioritises needs and learns about its body.
| Comments: | Accepted at IWAI 2026, forthcoming in the Springer proceedings. 17 pages: the 13-page camera-ready paper, reproduced without alteration apart from one typographical fix, followed by 4 pages of supplementary material. Code: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2610.18617 [cs.AI] |
| (or arXiv:2610.18617v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18617 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: St John Grimbly [view email]
[v1]
Tue, 13 Oct 2026 16:01:02 UTC (469 KB)
来源：arXiv cs.AI · arxiv.org