paperAugust 2026Unreviewed

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

P. Wang, Ao-Jie Yuan, Haiyu Zhang, Xi-Yang Hu, Yue Zhao, Shuli Jiang

Abstract

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners. Existing agent benchmark

Framework mappings

OWASP Top 10 for Agentic Applications

ASI02Tool Misuse & Exploitation

MITRE ATLAS

AML.T0053AI Agent Tool Invocation

Suggested from the entry's categories.

Cite

@misc{wang2026weclawarena,
  title = {{WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks}},
  author = {P. Wang and Ao-Jie Yuan and Haiyu Zhang and Xi-Yang Hu and Yue Zhao and Shuli Jiang},
  year = {2026},
  month = aug,
  eprint = {2608.03499},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/1cdb58ea64b231ab64a0e542ad7c793814345ad2}
}