AutoRAS自动构建抗攻击的智能体系统，提升大模型协同可靠性。
AutoRAS: Learning Robust Agentic Systems with Primitive Representations
- 用符号化原语序列表示智能体结构与行为，统一建模设计
- 在对抗环境下性能下降最小，优于现有方法
- 适合需要高鲁棒性的复杂多智能体应用
自动化设计智能体系统为扩展大语言模型（LLMs） beyond 单智能体推理提供了可行路径。尽管先前工作通过手工或自动生成的多智能体流程提升了任务性能，但鲁棒性常被忽视，导致系统易受外部攻击和内部故障影响。本文提出 AutoRAS，一个自动化鲁棒智能体系统设计框架。AutoRAS 将系统设计建模为生成一组符号化原语的序列，联合编码结构连接性与行为动作，并利用执行反馈的安全信号和基于流的序列级目标进行优化。大量实验表明，AutoRAS 在常规与对抗设置下均表现最优，且在攻击下的性能下降最小。进一步分析显示其具备强可迁移性、稳定优化行为、对原语集的稳定性以及有利的成本权衡。代码已开源。
原文摘要 · Abstract (English)
The automated design of agentic systems offers a promising pathway for scaling large language models (LLMs) beyond single-agent reasoning. While prior work has advanced task performance through handcrafted or automatically generated multi-agent workflows, robustness is often treated as an afterthought, leaving systems vulnerable to external adversaries and internal failures. We propose AutoRAS, a framework for the Automated design of Robust Agentic Systems. AutoRAS formulates system design as generating a sequence of symbolic primitives that jointly encode structural connectivity and behavioral actions, and learns to optimize this sequence using execution-derived safety signals and flow-based sequence-level objectives. Extensive experiments show that AutoRAS achieves the best performance in both vanilla and adversarial settings, with the smallest performance degradation under attacks. Further analyses demonstrate strong transferability, stable optimization behavior, stability across primitive sets, and favorable cost trade-offs. Our code is available at $\href{https://github.com/guohezuy/AutoRAS}{\text{this https URL}}$.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。