OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction
Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation. We introduce OntoAct, a hypothesis-based neuro-symbolic framework built on ontological abstraction. OntoAct turns individual experiences into axioms over entity types, relations, and conditions, making th...
Donghyeok Lee, Bong Gyun Kang, Junyong Ahn et al.
· 0 citations