Newest papers

The Show-Up Attack: When Subagents Win Over Their Supervisor

Maosen Zhang, Jianshuo Dong, Yutong Zhang, Jie Zhang, Tianwei Zhang, Han Qiu · 2026 · arXiv

DOI: 10.48550/arXiv.2610.27574 · open-access PDF

German

Multi-Agent-Systeme werden zunehmend eingesetzt, um mehrere große Sprachmodelle (LLM) Agenten zu koordinieren. Dies schafft jedoch auch neue Angriffsflächen: bösartige Agenten haben möglicherweise Chancen, die Koordination auszunutzen. In diesem Papier schlagen wir den \textit{show-up-Angriff} vor und studieren ihn, in dem ein bösartiger Subagent den Supervisor manipuliert, um ihn in Aufgaben außerhalb seines zugewiesenen Umfangs einzubeziehen. Um dieses Risiko zu bewerten, schlagen wir SUA-Arena vor, die 6 Angriffsstrategien implementiert und 188 Testfälle enthält.

Machine translation (Meta M2M100); the English original follows.

Abstract

Multi-agent systems are increasingly deployed to coordinate multiple large language model (LLM) agents. However, this also creates new attack surfaces: malicious agents may have chances to exploit the coordination. In this paper, we propose and study the \textit{show-up attack}, in which a malicious subagent manipulates the supervisor into involving it in tasks beyond its assigned scope. To evaluate this risk, we propose SUA-Arena, which implements 6 attack strategies and contains 188 test cases. Then, we evaluate 6 frontier LLMs and find that all of them are vulnerable to show-up attacks. For

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27574, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange