Localizing and Correcting Errors for LLM-based Planners

ArXi:2602.00276v2 Announce Type: replace Large language models (LLMs) have nstrated strong reasoning capabilities on math and coding, but frequently fail on symbolic classical planning tasks. Our studies, as well as prior work, show that LLM-generated plans routinely violate domain constraints given in their instructions (e.g., walking through walls). To address this failure, we propose iteratively augmenting instructions with Localized In-Context Learning (L-ICL) nstrations: targeted corrections for specific failing steps.