Why Cognitive Robotics Matters: Lessons from OntoAgent and LLM Deployment in HARMONIC for Safety-Critical Robot Teaming
This addresses the challenge of reliable and transparent long-horizon planning for safety-critical robot teaming, though it is incremental as it compares existing methods (LLMs vs. OntoAgent) within a specific architecture.
The study tackled the problem of deploying embodied AI agents in the physical world by evaluating whether LLMs can replicate the cognitive capabilities of OntoAgent in the HARMONIC architecture for safety-critical robot teaming, finding that LLMs do not consistently assess their own knowledge state, causing failures in diagnostic reasoning and action selection even with equivalent procedural knowledge.
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.