Papers, benchmarks, and commentary from mace AI, alongside research and development toward Deep Model Trust.
The technical white paper behind Fisher: adaptive multi-turn testing, action-level evidence, replay, remediation re-attack, and a learning strategy graph, documented across 50,000+ retained research episodes as of July 2026.
Gregory Frank proposes an approach to discovering and containing unauthorized coordination across AI agent executions. Evaluation remains prospective.
Read the overview and find the paper on arXiv → · Gregory Frank · September 5, 2026
Alongside Fisher, mace AI is researching specialized models, scoped authority for personal agents, policy-based decisions, and evidence-led release processes. These initiatives are in research and development and are not commercially available.
Articles and commentary from the mace AI team.
Explore Greg’s Counter-Swarm Doctrine on unauthorized collaboration, shared state, and recovery across agent runs.