# Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

arXiv: https://arxiv.org/abs/2603.03565 · HTML: https://mlsanity.com/paper/2603.03565/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 6 of 6)

- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents](https://mlsanity.com/paper/2503.01935/) (2025)
- [Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments](https://mlsanity.com/paper/2504.17087/) (2025)
- [LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?](https://mlsanity.com/paper/2509.21501/) (2025)

## Built on by (most cited first, 1 of 1)

- [SPEAR: Code-Augmented Agentic Prompt Optimization](https://mlsanity.com/paper/2605.26275/) (2026)

## Abstract (arXiv)

Conversational shopping assistants (CSAs) represent a compelling application of agentic AI, but moving from prototype to production reveals two underexplored challenges: how to evaluate multi-turn interactions and how to optimize tightly coupled multi-agent systems. Grocery shopping further amplifies these difficulties, as user requests are often underspecified, highly preference-sensitive, and constrained by factors such as budget and inventory. In this paper, we present a practical blueprint for evaluating and optimizing conversational shopping assistants, illustrated through a production-scale AI grocery assistant. We introduce a multi-faceted evaluation rubric that decomposes end-to-end shopping quality into structured dimensions and develop a calibrated LLM-as-judge pipeline aligned with human annotations. Building on this evaluation foundation, we investigate two complementary prompt-optimization strategies based on a SOTA prompt-optimizer called GEPA (Shao et al., 2025): (1) Sub-agent GEPA, which optimizes individual agent nodes against localized rubrics, and (2) MAMuT (Multi-Agent Multi-Turn) GEPA (Herrera et al., 2026), a novel system-level approach that jointly optimizes prompts across agents using multi-turn simulation and trajectory-level scoring. We release rubric templates and evaluation design guidance to support practitioners building production CSAs.