Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference

arXiv:2610.18617 · cs.AI, q-bio.NC · Submitted 2026-10-13 · Read on arXiv

cs.AI, q-bio.NC

Submitted: 2026-10-13

Updated: 2026-10-13

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: https://github.com/sgrimbly/interoceptive-prioritisation-iwai2026-snapshot

Code: https://github.com/sgrimbly/interoceptive-prioritisation-iwai2026-snapshot

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Active Inference — 1× in this paper · explained in 1 episode

Sources

• Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent
• Prior preferences in active inference agents: soft, hard, and goal shaping

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems