# AutoPDL: Automatic Prompt Optimization for LLM Agents

arXiv: https://arxiv.org/abs/2504.04365 · HTML: https://mlsanity.com/paper/2504.04365/

## Key facts

- Cited by 27 papers in the map (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 33 of its 46 references that are in the map.
- First posted on arXiv 6 Apr 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [Non-stochastic Best Arm Identification and Hyperparameter Optimization](https://mlsanity.com/paper/1502.07943/) (2015)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023)
- [Black-Box Prompt Optimization: Aligning Large Language Models without Model Training](https://mlsanity.com/paper/2311.04155/) (2023)
- [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://mlsanity.com/paper/2405.04324/) (2024)
- [EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms](https://mlsanity.com/paper/2406.14228/) (2024)
- [Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks](https://mlsanity.com/paper/2407.00121/) (2024)
- [START: Self-taught Reasoner with Tools](https://mlsanity.com/paper/2503.04625/) (2025)
- [Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars](https://mlsanity.com/paper/2405.16122/) (2024)
- [Prompt Optimization with Human Feedback](https://mlsanity.com/paper/2405.17346/) (2024)
- [Aviary: training language agents on challenging scientific tasks](https://mlsanity.com/paper/2412.21154/) (2024)
- [AlphaD3M: Machine Learning Pipeline Synthesis](https://mlsanity.com/paper/2111.02508/) (2021)
- [Localized Zeroth-Order Prompt Optimization](https://mlsanity.com/paper/2403.02993/) (2024)

## Built on by (most cited first, 27 of 27)

- [Position: The Real Barrier to LLM Agent Usability is Agentic ROI](https://mlsanity.com/paper/2505.17767/) (2025)
- [Prompt-MII: Meta-Learning Instruction Induction for LLMs](https://mlsanity.com/paper/2510.16932/) (2025)
- [SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback](https://mlsanity.com/paper/2505.19514/) (2025)
- [MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games](https://mlsanity.com/paper/2603.09022/) (2026)
- [How can we assess human-agent interactions? Case studies in software agent design](https://mlsanity.com/paper/2510.09801/) (2025)
- [Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use](https://mlsanity.com/paper/2602.20426/) (2026)
- [JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents](https://mlsanity.com/paper/2604.19821/) (2026)
- [Transduction is All You Need for Structured Data Workflows](https://mlsanity.com/paper/2508.15610/) (2025)
- [Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts](https://mlsanity.com/paper/2604.00901/) (2026)
- [Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning](https://mlsanity.com/paper/2607.05458/) (2026)
- [Self-Optimizing Multi-Agent Systems for Deep Research](https://mlsanity.com/paper/2604.02988/) (2026)
- [Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization](https://mlsanity.com/paper/2601.08682/) (2026)
- [Resolving Java Code Repository Issues with iSWE Agent](https://mlsanity.com/paper/2603.11356/) (2026)
- [When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models](https://mlsanity.com/paper/2603.19247/) (2026)
- [A Reproducible Optimisation Protocol for Calibrating Prompt-Based Large Language Model Workflows in Evidence Synthesis](https://mlsanity.com/paper/2605.06937/) (2026)
- [MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale](https://mlsanity.com/paper/2608.10333/) (2026)
- [Representing Prompting Patterns with PDL: Compliance Agent Case Study](https://mlsanity.com/paper/2507.06396/) (2025)
- [Synthetic Data-Driven Prompt Tuning for Financial QA over Tables and Documents](https://mlsanity.com/paper/2511.06292/) (2025)
- [CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization](https://mlsanity.com/paper/2604.14214/) (2026)
- [Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement](https://mlsanity.com/paper/2605.28360/) (2026)
- [Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model](https://mlsanity.com/paper/2606.07721/) (2026)
- [PPDL: LLM-Based Flows as Probabilistic Programs](https://mlsanity.com/paper/2608.05234/) (2026)
- [StepReflect: Structured UI Transition Reflection for Mobile GUI Agents](https://mlsanity.com/paper/2608.05587/) (2026)
- [Code-to-Harness: Distilling Black-Box Optimizers from Self-Play](https://mlsanity.com/paper/2609.09468/) (2026)
- [Failure-Guided Co-Evolution of Prompts and Training Data](https://mlsanity.com/paper/2609.15209/) (2026)
- [From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction](https://mlsanity.com/paper/2609.34829/) (2026)
- [Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests](https://mlsanity.com/paper/2609.38762/) (2026)

## Abstract (arXiv)

The performance of large language models (LLMs) depends on how they are prompted, with choices spanning both the high-level prompting pattern (e.g., Zero-Shot, CoT, ReAct, ReWOO) and the specific prompt content (instructions and few-shot demonstrations). Manually tuning this combination is tedious, error-prone, and specific to a given LLM and task. Therefore, this paper proposes AutoPDL, an automated approach to discovering good LLM agent configurations. Our approach frames this as a structured AutoML problem over a combinatorial space of agentic and non-agentic prompting patterns and demonstrations, using successive halving to efficiently navigate this space. We introduce a library implementing common prompting patterns using the PDL prompt programming language. AutoPDL solutions are human-readable, editable, and executable PDL programs that use this library. This approach also enables source-to-source optimization, allowing human-in-the-loop refinement and reuse. Evaluations across three tasks and seven LLMs (ranging from 3B to 70B parameters) show consistent accuracy gains (9.21±15.46 percentage points), up to 67.5pp, and reveal that selected prompting strategies vary across models and tasks.