Skip to content
Book Open access

Evolving Multi-Agent Systems with Large Language Models: Surrogate Fitness Limitations and Empirical Insights

Jul 2026 · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 0 citations · 23 references

Abstract

We investigate the use of large language models (LLMs) as evolutionary operators for optimizing the architecture of multi-agent systems (MAS) - a representative instance of LLM-driven optimization over attributed-graph artifacts that arise in generative design. Given a task description, an initial MAS configuration is generated and then refined on a per-task basis through two optimization strategies: (1) a population-based evolutionary approach where LLMs serve as mutation, crossover, and selection operators, with an LLM-as-a-Judge ensemble providing the surrogate fitness signal; and (2) a simpler iterative regeneration scheme that uses textual feedback from LLM judges to guide single-solution improvement without maintaining a population. We evaluate both approaches on the GAIA benchmark. Our experiments reveal a critical sensitivity to the judge model's quality: a capable judge (Claude 4 Sonnet) yields +14.3 and +6.67 percentage-point accuracy improvements for evolutionary and iterative approaches, respectively, whereas a weaker judge (Gemini-2.5-Flash) provides no benefit or even degrades performance below the unoptimized baseline. Both approaches incur substantial computational costs, raising questions about practical cost-effectiveness. These results highlight fundamental challenges of surrogate fitness functions in LLM-driven evolutionary optimization and offer practical insights for applying evolutionary methods to MAS architecture design.

Read PDF

Similar papers

Preprint Aug 2026

OptiMAS: Automatically Optimize Multi-Agent System

This work presents OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution and sustains performance improvement over extended optimization horizons.

Yuxin Cheng, Chang Liu, Hanxin Yu et al. · 0 citations
Book Open access Jul 2026

LLMigrate: Large Language Models as Migration Controllers in Island-Based Evolutionary Design of Soft Robots

This work proposes an LLM-guided migration controller for island-model evolutionary design, where an LLM receives compact summaries of island states including fitness statistics and morphology information and outputs migration decisions, and positions LLMs as coordinators of inter-island information flow in evolutionary robotics.

Emir Buğra Şahin, Ege Demir, Bilgehan Altıntaş et al. · 0 citations
Preprint Aug 2026

Automating Parent Selection Configuration in Genetic Programming with Agentic AI

Findings demonstrate the potential of agentic AI to translate domain knowledge into generating executable components, providing a step toward automated configuration and design of evolutionary systems.

Jose Guadalupe Hernandez, Jui-Hsuan Chang, A. Saini et al. · 0 citations
Preprint Jul 2026

Decision Protocols in Multi-Agent Large Language Model Conversations

This thesis introduces the Multi-Agent LLM (MALLM) framework, which implements and evaluates various decision protocols, namely voting, consensus, and judge decision mechanisms, to simulate multi-agent discussions for conversational task solving and indicates that consensus protocols excel in knowledge-intensive domains while voting and judge protocols are more effective for logic-based tasks.

Lars Benedikt Kaesberg · 0 citations
Preprint Jul 2026

An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery

Large language model coding agents increasingly perform open-ended data modeling and analysis. These agents are stochastic and adaptive, and therefore their autonomous model discovery behavior cannot be adequately characterized by a single benchmark run. In this work, we propose an experimental design and analysis framework for systematically evaluating this discovery process, quantifying its variability, and identifying important factors. The proposed framework treats these agents as stochastic model-discovery operators, which map task-specific discovery data and an optimization target to a fitted model. Specifically, we investigate two such operators, Codex and Claude Code, under controlled experimental factors including agent's reasoning effort, task, optimization metric, and composition of training data. For each agent-task-metric combination, regression models and inference are conducted for multiple responses such as output quality, dollar cost, wall-clock time, and process complexity. Furthermore, we develop a utility-aligned canonical decomposition to characterize the dominant direction of the reasoning-effort effect and to assess whether that direction aligns with a performance-cost utility direction. The proposed framework is demonstrated on a testbed of networked word-forming games with insightful findings on reasoning effort with respect to cost and process complexity.

Hao He, Xueying Liu, C. Kuhlman et al. · 0 citations