Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI methodology, we study embodied LLM agents behaviorally by varying the information available to the agent and measuring the resulting changes in behavior. Using the Lockbox, a sequential mechanical puzzle with hidden interdependencies, we evaluate LLMs across RGB, RGB-D, and ground-truth symbolic observations in a physical robotic setup and use controlled simulation to probe the resulting behavior. Counterintuitively, agents perform best under raw RGB input and worst under perfect ground-truth observations. In simulation, we probe this effect by randomly flipping perceived action outcomes and find that moderate noise improves performance, peaking at a 40% flip probability with a 2.85-fold success rate increase over the noise-free baseline. Further analysis links this gain to a reduction in repetitive action loops. These findings suggest that success rates alone are insufficient for evaluating LLMs, as measured performance may reflect the interaction between perceptual errors and reasoning failures rather than robust problem solving.

翻译：大型语言模型（LLMs）被越来越多地提出作为机器人系统的认知组件，但其不透明的决策过程使得解释闭环具身任务中的成功或失败变得困难。遵循经验性人工智能方法论，我们通过改变智能体可获得的信息并测量由此产生的行为变化，对具身LLM智能体进行行为学研究。使用Lockbox——一个具有隐藏相互依赖性的序列机械谜题——我们在物理机器人设置中评估了LLM在RGB、RGB-D和地面真实符号观察下的表现，并利用受控仿真探究由此产生的行为。与直觉相反，智能体在原始RGB输入下表现最佳，而在完美的地面真实观察下表现最差。在仿真中，我们通过随机翻转感知到的行动结果来探究这一效应，发现适度的噪声能提升性能，在40%的翻转概率下达到峰值，成功率较无噪声基线提高了2.85倍。进一步分析将该增益与重复行动循环的减少联系起来。这些发现表明，仅靠成功率不足以评估LLM，因为测量到的性能可能反映了感知误差与推理失败之间的交互作用，而非稳健的问题解决能力。