Auditable Claims about AI Agents

arXiv:2610.07459 · cs.AI, cs.CL, cs.CY, cs.MA · Submitted 2026-10-05 · Read on arXiv

cs.AI, cs.CL, cs.CY, cs.MA

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/yzhao062/auditable-claims

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes

Sources

• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
• Safety Cases: How to Justify the Safety of Advanced AI Systems
• Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes?
• Auditable Agents
• Audit Trails for Accountability in Large Language Models
• CatchBench: When Can an Agent Failure Be Caught?

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems