Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems

Abstract

Multi-agent applications delegate work across independently operated deployers. After an incident, a verifier must answer two questions: which deployer released the reported bytes, and whether each cross-deployer edge was authorized. Credentials establish who may act, but need not bind them to later output bytes or prove both deployers authorized a dynamically created edge. We present a two-layer attestation design for dynamic delegation without a shared authority, public log, or precommitted wo

Categories

@misc{liu2026attesting,
  title = {{Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems}},
  author = {Lifei Liu and Haoran Yu},
  year = {2026},
  month = aug,
  eprint = {2608.30387},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.30387}
}