Embodied Task Planning via Graph-Informed Action Generation with Large Language Models

ArXi:2601.21841v3 Announce Type: replace While Large Language Models (LLMs) have nstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning. Unlike open-ended text generation, embodied agents must decompose high-level intents into actionable sub-goals while adhering to the constraints of a dynamic environment. Standard LLM planners frequently fail to maintain strategy coherence over extended horizons due to context window limitations or hallucinate state transitions that violate environment constraints.