GROB multi-agent system investigates public internet traces for agent activity
GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
Cryptography and SecurityArtificial Intelligence
Summary
Sometimes it's hard to figure out what automated online agents are doing if you don't have direct access to their internal data. The authors created GROB, a system that collects and carefully preserves public internet information to help investigate these agents' actions. They showed this public information can become clearer and more useful over time as new related data appears. However, just using public traces can't definitively say who is behind the activity or fully track continuous identities of these agents, which remains a difficult problem.
What this means in practice
- •For online security teams: Identify and track suspicious automated activity on public networks when direct monitoring is unavailable using GROB's trace collection approach.
- •For digital forensics analysts: Preserve and analyze public internet records over time to support investigations of autonomous online agents using collected trace archives.
Authors
Chiara Bonfanti, Cataldo Basile
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.