GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity

2026-10-08

AI Summary

This study addresses the challenge of investigating autonomous agent activities using only public internet traces in the absence of privileged telemetry data. To this end, it proposes a multi-agent architecture that performs controlled, read-only data collection to preserve original observations and leverages public records, such as census identifiers, to enable cross-temporal evidence correlation. The primary contribution lies in demonstrating that sparse public traces possess "delayed value," wherein their informational content increases as new evidence emerges, thereby supporting retrospective attribution reconstruction. Experimental results successfully linked traces collected in September to specific requests made in June, validating both the efficacy and limitations of the proposed approach.

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.

Problem

• autonomous agents
• public-trace investigation
• multi-agent architecture
• agent identity
• digital forensics

Innovation

• Multi-Agent Architecture
• Public-Trace Investigation
• Autonomous Agents
• Read-Only Collection
• Agent Identity