Grounding Agent Reasoning in Image Schemas: A Neurosymbolic Approach to Embodied Cognition
This addresses the challenge of improving embodied AI agents' reasoning and interaction capabilities for more natural human-agent collaboration, though it appears incremental as it builds on existing theories and methods.
The paper tackles the problem of agent reasoning systems lacking fundamental conceptual structures used by humans, proposing a novel framework that bridges embodied cognition theory and agent systems by leveraging formal characterizations of image schemas to ground agent understanding, aiming to enhance efficiency, interpretability, and intuitive human-agent interactions.
Despite advances in embodied AI, agent reasoning systems still struggle to capture the fundamental conceptual structures that humans naturally use to understand and interact with their environment. To address this, we propose a novel framework that bridges embodied cognition theory and agent systems by leveraging a formal characterization of image schemas, which are defined as recurring patterns of sensorimotor experience that structure human cognition. By customizing LLMs to translate natural language descriptions into formal representations based on these sensorimotor patterns, we will be able to create a neurosymbolic system that grounds the agent's understanding in fundamental conceptual structures. We argue that such an approach enhances both efficiency and interpretability while enabling more intuitive human-agent interactions through shared embodied understanding.