发表机构
Univ. of Cape Town; Neuroscience Institute, Univ. of Cape Town; Laureate Institute for Brain Research; University of the Witwatersrand; INRS; Delft University of Technology（开普敦大学; 开普敦大学神经科学研究所; 劳雷尔脑研究所; 金山大学; 国家科学研究中心（加拿大）; 代尔夫特理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对有限感知带宽下的需求分配问题，构建主动推理觅食智能体，提出动态稳态优先级的内感受注意力机制，在AffectWorld实验中显著提升存活率，且收益同时作用于感知与规划，学习速度也更快。
AI 中文摘要
生物系统必须在有限感知带宽下调控相互竞争的需求，增强某一估计的精度会消耗对其他估计的增强能力，因此任何固定预算系统都需决定如何分配感知精度。本文以主动推理建模的觅食智能体为研究对象，该智能体需维持多项生理需求以存活。每一步中，智能体读取自身身体状态信念，识别最需关注的通道，将固定预算的内感受精度重新分配给该通道，使经精度塑造的似然同时用于信念更新与规划。在四通道觅食网格世界AffectWorld中，与相同预算下采用均匀精度的智能体相比，这种选择性分配使学习阶段的存活率提升一倍以上（11种布局下分别为0.414和0.199，每组含32个随机种子，配对聚类自助法检验p≤10⁻⁴）。两项进一步结果阐明了该机制：收益同时来自感知与规划，若仅剥夺规划所用的经塑造似然，收益会减少约一半；且该收益与需求对齐，将精度分配给最不需关注的通道时，性能差于均匀分配。受关注通道的动态学习速度约为其他通道的两倍，即使在相同观测数量下仍保持优势，这是精度路由的行为痕迹，可在学习速度而非存活率中观测到。
英文摘要
Biological systems must regulate competing needs under limited perceptual bandwidth, where sharpening one estimate costs the capacity to sharpen the others. Any fixed-budget system therefore has to decide where to allocate its perceptual precision. We study this in a foraging agent that must keep several bodily needs satisfied to survive, modelled with active inference. At each step it reads its own body-state beliefs, identifies the most-needed channel, and reallocates a fixed budget of interoceptive precision toward it, so that the same precision-shaped likelihood feeds both belief update and planning. In AffectWorld, a four-channel foraging gridworld, this selective allocation more than doubles learning-phase survival at matched budget against a uniform-precision agent ($0.414$ vs $0.199$ across 11 layouts, $n{=}32$ seeds each, paired cluster-bootstrap $p \leq 10^{-4}$). Two further results sharpen the mechanism. The benefit runs through planning as well as perception, since denying the shaped likelihood to the planner alone removes about half of it. It is also need-aligned, since aiming precision at the least-needed channel does worse than spreading it evenly. The attended channel additionally learns its own dynamics about twice as fast, and stays ahead even at matched observation count, a behavioural trace of the same precision routing, visible in learning speed, not survival.
CommentsAccepted at SAB 2026 (From Animals to Animats 18), forthcoming in the Springer Lecture Notes in Artificial Intelligence proceedings. 20 pages, 11 numbered figures (12 graphics), 5 tables. The 12-page camera-ready paper is reproduced without alteration and followed by supplementary analyses that were not part of the proceedings paper. Code: https://github.com/sgrimbly/attention-aif-sab2026-snapshot
