Localizing and Correcting Errors for LLM-based Planners
This addresses the issue of unreliable LLM-based planners for symbolic planning domains, representing an incremental improvement over existing in-context learning methods.
The paper tackles the problem of LLMs frequently violating domain constraints in symbolic classical planning tasks by proposing Localized In-Context Learning (L-ICL), which iteratively adds targeted corrections for failing steps, resulting in valid plans 89% of the time on an 8x8 gridworld compared to 59% for the best baseline.
Large language models (LLMs) have demonstrated 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) demonstrations: targeted corrections for specific failing steps. Specifically, L-ICL identifies the first constraint violation in a trace and injects a minimal input-output example giving the correct behavior for the failing step. Our proposed technique of L-ICL is much effective than explicit instructions or traditional ICL, which adds complete problem-solving trajectories, and many other baselines. For example, on an 8x8 gridworld, L-ICL produces valid plans 89% of the time with only 60 training examples, compared to 59% for the best baseline, an increase of 30%. L-ICL also shows dramatic improvements in other domains (gridworld navigation, mazes, Sokoban, and BlocksWorld), and on several LLM architectures.