Procedural Knowledge Improves Agentic LLM Workflows

2025-11-10

AI Summary

Large language models (LLMs) struggle with implicit planning–oriented agent tasks due to heavy reliance on extensive tool integration, manual prompt engineering, or costly fine-tuning. Method: This paper proposes explicitly modeling domain-specific procedural knowledge as Hierarchical Task Networks (HTNs), integrating both handcrafted and LLM-generated HTNs into the reasoning process to guide task decomposition and execution. Contribution/Results: Experiments demonstrate that HTN augmentation significantly improves task success rates—20B/70B LLMs outperform a 120B baseline, and handcrafted HTNs enable smaller models to surpass larger ones, confirming that knowledge-driven structuring can meaningfully offset architectural scale disadvantages. This work formally establishes HTNs as an effective mechanism for enhancing LLM-based agents, revealing the critical role of structured procedural knowledge in agent design. It introduces a new paradigm for building lightweight, interpretable, and high-performance LLM agents grounded in explicit task hierarchies.

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Cognitive Modeling & Cognitive Systems: Agent ArchitecturesNatural Language Processing: (Large) Language Models

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSearch and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

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.

Problem

• LLMs struggle with agentic tasks without extensive support
• Procedural knowledge potential for LLM agentic tasks understudied
• Hierarchical task networks improve LLM performance on agentic tasks

Innovation

• Uses hierarchical task networks for procedural knowledge
• Hand-coded HTNs dramatically improve LLM performance
• LLM-created HTNs also enhance overall workflow performance