Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents
Xiao, Frank, Phuong, MaryarXiv.orgPublished Jun 10, 2026Original︎ ↗Archived copy
Examinations
None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.
Text53 passages · 0 marked
No claim quotes it yet.
Not found in the text 2
But as the capability gap widens and CoT transparency degrades with scale, both signals weaken.
Not yet read by this claim’s Steward.
Trusted monitoring is a cornerstone of AI control. However, as frontier models grow more capable, the increasing capabilities gap between trusted and untrusted models may render trusted models unreliable monitors. [...] Bootstrapped monitoring substantially improves catch rates over trusted-only monitoring, even when the untrusted monitor actively colludes with the agent, provided we have access to its raw chain-of-thought.
Not yet read by this claim’s Steward.
Lineage across 2 claims
Record
- Kind
- unknown
- Authors
- Xiao, Frank, Phuong, Mary
- Publisher
- arXiv.org
- Published
- Jun 10, 2026
- DOI
- None
- Link
- https://arxiv.org/abs/2606.11998
- Archived copy
- https://web.archive.org/web/20260731160204/https://arxiv.org/abs/2606.11998
- Stored text
- 4,448 characters, retrieved Nov 11, 2026 · 47 sections, 53 passages
- Claims extracted
- Not recorded
- Versions
- One known
- Copies
- None recorded
- Corrections
- None recorded
- Facts checked
- Nov 11, 2026
History 3
- Nov 11, 2026DividedSegmenter · Divided into 100 parts by its own structure
- Nov 11, 2026FactsFacts fetcher · Facts looked up
- Nov 11, 2026Entered the graphEntered the graph; copy stored