mlsanityData to 14 Oct 2026

Representing Prompting Patterns with PDL: Compliance Agent Case Study

arXiv 2507.06396 ↗First posted 8 Jul 2025cs.AI cs.LG cs.PLcited by 0

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

Abstract (arXiv)

Prompt engineering for LLMs remains complex, with existing frameworks either hiding complexity behind restrictive APIs or providing inflexible canned patterns that resist customization -- making sophisticated agentic programming challenging. We present the Prompt Declaration Language (PDL), a novel approach to prompt representation that tackles this fundamental complexity by bringing prompts to the forefront, enabling manual and automatic prompt tuning while capturing the composition of LLM calls together with rule-based code and external tools. By abstracting away the plumbing for such compositions, PDL aims at improving programmer productivity while providing a declarative representation that is amenable to optimization. This paper demonstrates PDL's utility through a real-world case study of a compliance agent. Tuning the prompting pattern of this agent yielded up to 4x performance improvement compared to using a canned agent and prompt pattern.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 11 of its 17 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

11 of 17 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025AutoPDL: Automatic Prompt Optimization for LLM Agents6 Apr
  2. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms20 Jun

Other references · 9

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  4. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  5. 2023Efficient Guided Generation for Large Language Modelscited by 200
  6. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  7. 2022Prompting Is Programming: A Query Language for Large Language Modelscited by 110
  8. 2025ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Taskscited by 51
  9. 2024PDL: A Declarative Prompt Programming Languagecited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language
  2. 2025A Taxonomy of Prompt Defects in LLM Systems
  3. 2024Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts
  4. 2026MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
  5. 2025Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap
  6. 2026AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents
  7. 2026Prompt Coach: An Empirical Evaluation of an Agentic Tutor for Learning Prompt Engineering in Software Development
  8. 2026Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code