AgentBalance: Backbone-then-Topology Design for Cost-Effective Multi-Agent Systems under Budget Constraints

TL;DR

AgentBalance introduces a backbone-then-topology framework for cost-effective multi-agent systems that optimizes performance under explicit token-cost and latency budgets, improving deployment efficiency.

Contribution

It proposes a novel backbone-then-topology design approach that models and optimizes multi-agent systems under explicit deployment constraints, outperforming existing methods.

Findings

Achieves up to 10% performance gains under token-cost budgets.

Achieves up to 22% performance gains under latency budgets.

Generalizes well to unseen LLMs for practical deployment.

Abstract

Large Language Model (LLM)-based multi-agent systems (MAS) are becoming indispensable building blocks for web-scale applications such as web search, social network analytics, and online customer support, where cost-effectiveness is increasingly the primary constraint for large-scale deployment. While recent work improves MAS cost-effectiveness by shaping inter-agent communication topologies and selecting agent backbones, it rarely models and optimizes under explicit token-cost and latency budgets that reflect deployment constraints. This often leads to topology-first designs and suboptimal cost-effectiveness when budgets are binding. We present AgentBalance, a framework for constructing cost-effective MAS under explicit token-cost and latency budgets via a backbone-then-topology design. AgentBalance first performs backbone-oriented agent generation, constructing agents with heterogeneous backbones through LLM pool construction, pool selection, and role-backbone matching. It then performs adaptive MAS topology generation, guiding inter-agent communication via agent representation learning, gating, and latency-aware topology synthesis. Experiments on benchmarks with 14 candidate LLM backbones show that AgentBalance achieves up to 10% and 22% performance gains under matched token-cost and latency budgets, respectively, and yields strong AUC on performance-versus-budget curves across benchmarks. AgentBalance also functions as a plug-in for existing MAS, improving performance under the same token-cost and latency constraints, and it generalizes well to unseen LLMs for practical, budget-aware deployment. Code: https://github.com/usail-hkust/AgentBalance