Procedural Knowledge Improves Agentic LLM Workflows
Hsiao, Vincent, Roberts, Mark, Smith, Leslie
–arXiv.org Artificial Intelligence
Large language models (LLMs) often struggle when performing agentic tasks without substantial tool support, prom-pt engineering, or fine tuning. Despite research showing that domain-dependent, procedural knowledge can dramatically increase planning efficiency, little work evaluates its potential for improving LLM performance on agentic tasks that may require implicit planning. We formalize, implement, and evaluate an agentic LLM workflow that leverages procedural knowledge in the form of a hierarchical task network (HTN). Empirical results of our implementation show that hand-coded HTNs can dramatically improve LLM performance on agentic tasks, and using HTNs can boost a 20b or 70b parameter LLM to outperform a much larger 120b parameter LLM baseline. Furthermore, LLM-created HTNs improve overall performance, though less so. The results suggest that leveraging expertise--from humans, documents, or LLMs--to curate procedural knowledge will become another important tool for improving LLM workflows.
arXiv.org Artificial Intelligence
Nov-12-2025
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America > United States
- California
- San Diego County > San Diego (0.04)
- San Francisco County > San Francisco (0.14)
- District of Columbia > Washington (0.04)
- New York (0.04)
- California
- Europe > United Kingdom
- Genre:
- Research Report > New Finding (0.48)
- Workflow (1.00)
- Industry:
- Consumer Products & Services > Travel (0.68)
- Government > Military (0.46)
- Technology: