Local Ai
Localizing and Correcting Errors for LLM-based Planners
arXiv:2602.00276v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities on math and coding, but frequently fail on symbolic classical planning
arXiv:2602.00276v3 Announce Type: replace Abstract: 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.
Related
- Efficient LLM Collaboration via Planning
- Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
- In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
- Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models
- LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning
Source: arXiv cs.AI | 2026-09-10