paper-with-me

Papers

Representing Prompting Patterns with PDL: Compliance Agent Case Study

2025-07-08 · Mandana Vaziri, Louis Mandel, Yuji Watanabe, Hirokuni Kitahara, Martin Hirzel, Anca Sailer 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.

📄 PDF Abstract BibTeX arXiv:2507.06396

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Constrained Process Maps for Multi-Agent Generative AI Workflows

2026-02-02 · Ananya Joshi, Michael Rudow arxiv

Large language model (LLM)-based agents are increasingly used to perform complex, multi-step workflows in regulated settings such as compliance and due diligence. However, many agentic architectures rely primarily on pro…

Prompt Engineering

CompAgent: An Agentic Framework for Visual Compliance Verification

2025-10-31 · Rahul Ghosh, Baishali Chaudhury, Hari Prasanna Das, Meghana Ashok 외 arxiv

Visual compliance verification is a critical yet underexplored problem in computer vision, especially in domains such as media, entertainment, and advertising where content must adhere to complex and evolving policy rule…

Multimodal Reasoning

Prompt Engineering a Schizophrenia Chatbot: Utilizing a Multi-Agent Approach for Enhanced Compliance with Prompt Instructions

2024-10-10 · Per Niklas Waaler, Musarrat Hussain, Igor Molchanov, Lars Ailo Bongo 외

Patients with schizophrenia often present with cognitive impairments that may hinder their ability to learn about their condition. These individuals could benefit greatly from education platforms that leverage the adapta…

ChatbotEthicsPrompt Engineering

LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements

2025-05-29 · Jianwei Wang, Mengqi Wang, Yinsi Zhou, Zhenchang Xing 외

Health, Safety, and Environment (HSE) compliance assessment demands dynamic real-time decision-making under complicated regulations and complex human-machine-environment interactions. While large language models (LLMs) h…

Legal Reasoning

AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents

2026-07-01 · Laïla Elkoussy, Julien Perez arxiv

Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges. Neither captures how an answer was produced. In safety-critical settings, the procedure itself is part of correctness. In this paper,…