Problem
Research questions and friction points this paper is trying to address.
Multi-Agent Systems
evolutionary instability
branch-and-discard search
optimization scope
OptiMAS: Automatically Optimize Multi-Agent System
🤖 AI Summary
本文提出OptiMAS，通过统一的ReAct基础架构和双轨记忆机制，解决多智能体系统自动优化中范围与稳定性之间的权衡问题。
📝 Abstract
Automated evolution of Multi-Agent Systems (MAS) holds significant potential for reducing the manual effort required to design and optimize LLM-based agent architectures. However, extant search-based paradigms face a fundamental trade-off, where an expanded optimization scope exacerbates evolutionary instability, while discrete branch-and-discard search isolates insights across lineages. To address these limitations, we propose a continuous, data-driven optimization paradigm built upon a unified ReAct-based infrastructure that reconciles a broad optimization scope with operational stability. Under this paradigm, we present OptiMAS, a task-agnostic agentic optimizer that leverages textual interaction trajectories and task feedback as loss signals for end-to-end MAS evolution. Equipped with a novel dual-track memory mechanism, OptiMAS sustains performance improvement over extended optimization horizons. Evaluation on four heterogeneous agentic benchmarks with three varying scale and accessibility LLM backbones, demonstrates that OptiMAS consistently achieves competitive or superior accuracy relative to both domain-specialized hand-crafted systems and existing evolutionary methods. Our work establishes a practical milestone toward robust, automated MAS evolution.
Innovation
Methods, ideas, or system contributions that make the work stand out.
continuous data-driven optimization
ReAct-based infrastructure
dual-track memory mechanism
end-to-end MAS evolution
🔎 Similar Papers
No similar papers found.
