Answers are grounded in this paper and cite their sources.
We present an Artificial Intelligence with Symbolic Empathy, where an agent A cooperatively aligns a person’s cognitive state X⃗P(t) with their ideal trajectory X⃗LP(t) . Alignment is guided by a context-sensitive, non-monotonic logic LA implemented as a five-stage Hierarchical FSM: Identify (fact structuring), Classify (pattern extraction), Explore (intervention generation), Plan (ontology-based misalignment diagnosis), and Reason (abductive hypothesis evaluation). Reasoning is driven by the Shannon-von Neumann insight gain ISN(γ ᵢ) = [ H(BP(t)) - H(BP⁽ⁱ⁾(t+1)) ] · U(γ ᵢ), combining entropy reduction with goal-relevant utility. This metric enables self-supervised abductive learning, refining A ’s theory-of-mind and guiding psychologically meaningful, uncertainty-reducing interventions. The architecture ensures interpretability (I-AI), explainability (X-AI), and trustworthiness (T-AI) via explicit fact-rule tracing. Cognitive-cooperative case studies show that integrating symbolic causal models with utility-guided abductive-deductive reasoning yields transparent, goal-aligned human-AI interaction.
No takes yet. Share an insight, caveat, or question.
Edouard Siregar (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: