arXiv：cs.AI· Chiara Bonfanti, Cataldo Basile·· 3 小时前
GROB：基于公开痕迹调查候选智能体活动的多智能体架构
GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
AI 导读
GROB 是一种多智能体架构，可在无特权遥测数据时通过公开互联网痕迹调查候选自主智能体活动，执行受控只读采集并保留观测记录以供后续解析。在 2026 年 9 月的冻结语料中，9 月 9 日捕获的 Census 标识符经公开修订记录回溯，被解析为 6 月 16-17 日的具体 Census 请求；其他痕迹与后续证据的关联强度不一。
正文
Abstract:We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telemetry is unavailable. The system performs controlled, read-only collection of public traces and preserves selected observations for later resolution. In a frozen September 2026 corpus, several collected traces became more informative as additional public evidence emerged. The strongest result concerns Census-labelled identifiers captured on 9 September. Public revision records later resolved these identifiers to specific Census requests from 16 - 17 June. Other results show weaker links between traces collected by GROB and evidence reconstructed or reported later. These links vary in strength, and only some can be tied to specific public records. The results show that sparse public traces can remain useful even before their significance is fully understood. Such evidence can support later reconstruction, but public traces alone do not establish organizational attribution. Execution identity presents a separate problem, as continuity of agent identity remains an active research question for autonomous language-model agents.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11467 [cs.CR] |
| (or arXiv:2610.11467v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11467 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chiara Bonfanti [view email]
[v1]
Thu, 8 Oct 2026 08:17:45 UTC (6,190 KB)
来源：arXiv：cs.AI · arxiv.org