mlsanityData to 7 Oct 2026

Procedural Knowledge Improves Agentic LLM Workflows

arXiv 2511.07568 ↗First posted 10 Nov 2025cs.AIcited by 7

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 25 of its 45 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

25 of 45 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning15 Mar
  2. 2024Understanding the planning of LLM agents: A survey5 Feb
  3. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents2 Feb
  4. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar
  6. 2023Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs15 Mar

Other references · 19

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  5. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 298
  6. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 250
  7. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  8. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  9. 2022PromptChainer: Chaining Large Language Model Prompts through Visual Programmingcited by 134
  10. 2024Can Large Language Models Reason and Plan?cited by 82
  11. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  12. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
7 more
  1. 2024ACPBench: Reasoning about Action, Change, and Planningcited by 37
  2. 2024Robust Planning with LLM-Modulo Framework: Case Study in Travel Planningcited by 34
  3. 2023Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughtscited by 27
  4. 2024Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1cited by 17
  5. 2024Compressing Long Context for Enhancing RAG with AMR-based Concept Distillationcited by 16
  6. 2025Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planningcited by 15
  7. 2025Universal Deep Research: Bring Your Own Model and Strategycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
  2. 2026From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skillscited by 5
  3. 2026Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Costcited by 4
  4. 2026In-Context Prompting Obsoletes Agent Orchestration for Procedural Taskscited by 2
  5. 2026Experiments in Agentic AI for Sciencecited by 0
  6. 2026Procedural Knowledge Is Not Low-Rank: Why LoRA Fails to Internalize Multi-Step Procedurescited by 0
  7. 2026AgBench: Agentic AI Benchmarks for Personal AI Devicescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Scaling LLM Planning: NL2FLOW for Parametric Problem Generation and Rigorous Evaluation
  2. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
  3. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
  4. 2026Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation
  5. 2025Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents
  6. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
  7. 2024FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
  8. 2024Coalitions of Large Language Models Increase the Robustness of AI Agents