Guo-An Zhang

Zero-Shot Embodied Decision Making with Structured Prior Knowledge and Adaptive Calibration in ALFWorld

Large-language-model (LLM) agents perform well in embodied benchmarks but are costly, stochastic, and difficult to audit. We propose an LLM-free zero-shot decision agent for ALFWorld that combines structured commonsense priors with adaptive calibration. The agent uses object-location priors, task templates, synonym map...