@misc{traceprobe,
  title = {TraceProbe: An Execution-Based Benchmark for Diagnosing Safety Failures in LLM Agents},
  url = {https://aclanthology.org/2026.emnlp-main.1233.pdf},
  author = {Yuxiang He and Jian Zhao and Yufei Liu and Yuchen Yuan and Xuelong Li},
  version = {Original resource captured 2026-10-28T07:24:41.534922+00:00; sha256:b0b85491f4be9fb842c2f97891b033a75b44a85c756b0f3b92cf8da775d8f828},
  note = {Original resource captured 2026-10-28T07:24:41.534922+00:00; sha256:b0b85491f4be9fb842c2f97891b033a75b44a85c756b0f3b92cf8da775d8f828}
}

@misc{traceprobe-nuwa,
  title = {TraceProbe: An Execution-Based Benchmark for Diagnosing Safety Failures in LLM Agents — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/traceprobe/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--traceprobe.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--traceprobe.json.}
}
