Tag
This paper argues that AI agent safety should be enforced at runtime via preventive controls and verifiable evidence, rather than relying solely on training-time alignment. It grounds the position in audits of safety incidents, false completions, trajectory schemas, and publication trends.
This paper introduces Evidence Chain Evaluation (ECE), a selective fact-checking framework that allows LLM-based verification agents to abstain from giving verdicts when evidence is weak, sparse, or inconsistent. On ECE-Bench, ECE achieves 97.8% selective accuracy at 93.7% coverage, demonstrating a safety-oriented trade-off for handling epistemically weak evidence.
Apodex 1.0 is a heavy-duty AI agent team for deep research that achieves state-of-the-art performance by searching the web, reasoning over evidence, and producing reports with verifiable evidence chains.