Why Cognitive Robotics Matters: Lessons from OntoAgent and LLM Deployment in HARMONIC for Safety-Critical Robot Teaming

TL;DR

This paper introduces HARMONIC, a cognitive-robotic architecture combining OntoAgent with a reactive layer, and evaluates whether large language models can replicate its cognitive functions in safety-critical robot teaming.

Contribution

It demonstrates that LLMs cannot reliably emulate OntoAgent's cognitive capabilities, highlighting the importance of deterministic architectures for embodied AI in safety-critical applications.

Findings

LLMs fail to assess their knowledge state before acting.

Downstream diagnostic and action failures occur with LLMs.

Architectural determinism is crucial for reliable embodied AI.

Abstract

Deploying embodied AI agents in the physical world demands cognitive capabilities for long-horizon planning that execute reliably, deterministically, and transparently. We present HARMONIC, a cognitive-robotic architecture that pairs OntoAgent, a content-centric cognitive architecture providing metacognitive self-monitoring, domain-grounded diagnosis, and consequence-based action selection over ontologically structured knowledge, with a modular reactive tactical layer. HARMONIC's modular design enables a functional evaluation of whether LLMs can replicate OntoAgent's cognitive capabilities, evaluated within the same robotic system under identical conditions. Six LLMs spanning frontier and efficient tiers replace OntoAgent in a collaborative maintenance scenario under native and knowledge-equalized conditions. Results reveal that LLMs do not consistently assess their own knowledge state before acting, causing downstream failures in diagnostic reasoning and action selection. These deficits persist even with equivalent procedural knowledge, indicating the issues are architectural rather than knowledge-based. These findings support the design of physically embodied systems in which cognitive architectures retain primary authority for reasoning, owing to their deterministic and transparent characteristics.