arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.08386cs.MAcs.AIcs.CLcs.CRcs.DC
收藏

无信任环境中智能体的自监督推理

Self-Supervised Inference of Agents in Trustless Environments

Fortytwo

Vladyslav Larin, Ivan Nikitin, Alexander Firsov

AI总结:

针对无信任环境下的智能体推理问题,提出基于LLM分类器的集群自监督推理方法,通过集体智慧实现去中心化AI推理,在准确性、安全性、可靠性及速度上均优于现有方案。

摘要:

本文提出了一种新颖方法,可让智能体组成集群以高效生成高质量响应。该方法通过利用具备数据推理与排序能力的智能体实现,可采用大语言模型(LLMs)作为响应分类器来有效落地。我们评估了现有的无信任智能体推理方案,定义了自身的研究方法,估算了实用参数,并对各类恶意智能体攻击进行了建模。本方法借助集群的集体智慧,可实现稳健高效的去中心化AI推理,具备更优的准确性、安全性与可靠性。实验表明,我们的方法比其他无信任推理策略速度快一个数量级,验证延迟低于125毫秒。

英文摘要:

In this paper, we propose a novel approach where agents can form swarms to produce high-quality responses effectively. This is accomplished by utilizing agents capable of data inference and ranking, which can be effectively implemented using LLMs as response classifiers. We assess existing approaches for trustless agent inference, define our methodology, estimate practical parameters, and model various types of malicious agent attacks. Our method leverages the collective intelligence of swarms, ensuring robust and efficient decentralized AI inference with better accuracy, security, and reliability. We show that our approach is an order of magnitude faster than other trustless inference strategies reaching less than 125 ms validation latency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑