# Maestro: Joint Graph & Config Optimization for Reliable AI Agents

arXiv: https://arxiv.org/abs/2509.04642 · HTML: https://mlsanity.com/paper/2509.04642/

## Key facts

- Cited by 9 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 12 of its 20 references that are in the map.
- First posted on arXiv 4 Sep 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, 12 of 12)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [Generalizing Verifiable Instruction Following](https://mlsanity.com/paper/2507.02833/) (2025)
- [AgentScope: A Flexible yet Robust Multi-Agent Platform](https://mlsanity.com/paper/2402.14034/) (2024)
- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)

## Built on by (most cited first, 9 of 9)

- [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026)
- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)
- [Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0](https://mlsanity.com/paper/2607.14004/) (2026)
- [JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents](https://mlsanity.com/paper/2604.19821/) (2026)
- [TextBO: Bayesian Optimization in Language Space for Eval-Efficient Self-Improving AI](https://mlsanity.com/paper/2511.12063/) (2025)
- [MedDCR: Learning to Design Agentic Workflows for Medical Coding](https://mlsanity.com/paper/2511.13361/) (2025)
- [On the Difficulty of Selecting Few-Shot Examples for Effective LLM-based Vulnerability Detection](https://mlsanity.com/paper/2510.27675/) (2025)
- [Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM](https://mlsanity.com/paper/2604.09418/) (2026)
- [Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference](https://mlsanity.com/paper/2607.02882/) (2026)

## Abstract (arXiv)

Building reliable LLM agents requires decisions at two levels: the graph (which modules exist and how information flows) and the configuration of each node (models, prompts, tools, control knobs). Most existing optimizers tune configurations while holding the graph fixed, leaving structural failure modes unaddressed. We introduce Maestro, a framework-agnostic holistic optimizer for LLM agents that jointly searches over graphs and configurations to maximize agent quality, subject to explicit rollout/token budgets. Beyond numeric metrics, Maestro leverages reflective textual feedback from traces to prioritize edits, improving sample efficiency and targeting specific failure modes. On the IFBench and HotpotQA benchmarks, Maestro consistently surpasses leading prompt optimizers--MIPROv2, GEPA, and GEPA+Merge--by an average of 12%, 4.9%, and 4.86%, respectively; even when restricted to prompt-only optimization, it still leads by 9.65%, 2.37%, and 2.41%. Maestro achieves these results with far fewer rollouts than GEPA. We further show large gains on two applications (interviewer & RAG agents), highlighting that joint graph & configuration search addresses structural failure modes that prompt tuning alone cannot fix.