研究人员开发了 MAP-Graph，这是一种新颖的内存层，旨在增强由大型语言模型驱动的多代理工作流的安全性和可靠性。该系统构建了一个来源感知的执行图，以仔细跟踪信息的来源，确保仅使用可接受和受信任的数据来进行代理操作。MAP-Graph 包含权限过滤、乘法路径信任和风险敏感操作门控等功能，显著提高了复杂场景下的任务成功率和决策准确性。 AI
影响 通过改进数据来源和访问控制，增强了基于 LLM 的多代理系统的安全性和可靠性。
排序理由 该集群包含一篇详细介绍多代理系统新技术方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2608.10509v1 Announce Type: new Abstract: Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action. Because restrictions propagate through derivations, summaries can conce…
arXiv:2608.11022v1 Announce Type: cross Abstract: Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their context, parameters, limitations, and intended use. However, these practices remain…
Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action. Because restrictions propagate through derivations, summaries can conceal private, poisoned, untrusted, or revoked sour…