对比大模型与认知架构在机器人协作中的表现，发现前者缺乏自我评估能力。
Why Cognitive Robotics Matters: Lessons from OntoAgent and LLM Deployment in HARMONIC for Safety-Critical Robot Teaming
- 用认知架构与大模型在相同系统中对比，验证其推理能力差异。
- 六种大模型均无法稳定评估自身知识状态，导致诊断和决策失败。
- 适合关注安全关键型机器人系统设计的研究者参考。
将具身人工智能代理部署于物理世界需具备长期规划的认知能力，以实现可靠、确定且透明的执行。本文提出HARMONIC认知机器人架构，结合内容中心的认知框架OntoAgent（具备元认知自监控、领域基础诊断及基于后果的动作选择）与模块化反应战术层。该架构支持在相同机器人系统、相同条件下，对六种覆盖前沿与高效层级的大语言模型（LLM）是否可复现OntoAgent的认知能力进行功能评估。实验在协作维护场景中进行，分别在原生和知识等价条件下测试。结果表明，大模型无法持续评估自身知识状态即执行动作，引发下游诊断推理与动作选择失败。此类缺陷即使在程序性知识相当的情况下依然存在，说明问题源于架构本质而非知识量。研究支持在具身系统中由认知架构主导推理，因其具备确定性和透明性优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。