Skip to content
Preprint

Design and Tuning of Multi-Agent Systems Using Bayesian Evolutionary Optimization

Oct 2026 · 0 citations · 24 references
Computer Science

Abstract

Designing effective multi-agent systems (MAS) remains a challenging and resource-intensive task. We propose a Bayesian Evolutionary Optimization framework for automatically discovering task-specific MAS topologies. The approach combines evolutionary operators to generate diverse workflow graphs with Bayesian optimization to focus cost intensive evaluations on promising candidates. In contrast to LLM-based candidate selection, our approach uses a graph-aware Gaussian Process and Expected Improvement to provide an explicit selection criterion during evolutionary search. We evaluate the method on BigCodeBench for code generation and on a tabular preprocessing benchmark using TabPFN. On BigCodeBench, evolved architectures achieve the highest overall performance among the evaluated agent systems. On temporal tabular datasets, optimized MAS preprocessing improves over the default TabPFN model on several tasks, while remaining competitive on IID datasets. Overall, the results demonstrate the potential of Bayesian selection for guiding evolutionary MAS search under expensive evaluation budgets.

View source

Similar papers

Book Open access Nov 2026

An Automated Multi-Agent Search-then-Evolution Framework for Lifetime Value Prediction

This work proposes AgentLTV, an automated multi-agent search-then-evolution framework for lifetime value prediction that uses MCTS for rapid adaptation to new data patterns, use EA for stable refinement, and validate deployment readiness with bucket-level ranking and calibration diagnostics.

Chao-Wei Wu, Hua-Zhu Chen, Qi-Rui Yang et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery

The discovery and development of advanced materials is a challenging process constrained by the high time and monetary costs of synthesis, processing, and characterization. The underlying design spaces can be enormous, often with multiple competing objectives. Bayesian optimization (BO) provides a principled approach f...

Robert Robinson, S. P. Padhy, S. Sinha et al. · 0 citations
#large language models Open access Oct 2026

ParaOpt-Agent: A Knowledge-Driven Decision Agent for Simulation Model Parameter Optimization

Simulation model parameter optimization requires selecting optimizers from task knowledge and translating those decisions into execution configurations that satisfy interface, authorization, and budget requirements. We propose ParaOpt-Agent, a knowledge-driven pre-execution agent that combines task and optimizer descri...

Dan-Yang Jiang, Minghui Lyu, Zhao-Pen Liu et al. · 0 citations

Multi-Agent System Search via Active Substructure-aware Policy Optimization

ASPO introduces an Adaptive Query-Selection Mechanism (AQSM) that focuses training on queries at the policy's competence boundary: those it can solve but not yet reliably, and introduces substructure-level rewards that measure output-quality gains within each action's descendant subgraph.

Bei-Cheng Xu, Bo-Wen Fan, Wei Qian et al. · 0 citations
Preprint Oct 2026

Not Every Agent Needs the Strongest Model: Unified Prompt-Model Optimization for Heterogeneous LLM-based Multi-Agent Systems

Large language model (LLM)-based multi-agent systems (MAS) rely on role-specific prompts and execution models to solve complex tasks collaboratively. However, prompt optimization typically keeps model assignments fixed, leaving differences in role requirements and their associated inference costs outside the search. We...

Ming-Xiu Cai, Hao-Yang Xian, Xin-Yu Ma et al. · 0 citations
#artificial intelligence Open access Sep 2026

Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent Systems

This work systematically evaluates 8 model selection strategies across before-generation (routing) and after-generation (majority-voting, LLM-as-a-judge) MAS architectures on challenging scientific benchmarks and finds that candidate selection within a single model family is the strategy that yields the best relative p...

Sara Vera Marjanovic, Jia-Chen Xu, A. Laptev et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.