Skip to main content
Search

# CIEG

1 related articles

Subscribe to updates
  1. arXiv

    Medical agents stop treating every tool output as evidence: CIEG rules first, reaching 0.730 balanced accuracy in glaucoma screening

    Tool-augmented medical agents treat whatever their tools return as evidence, and a frozen reasoner cannot ignore what enters its context, so a wrong output flips cases it would otherwise answer correctly. CIEG moves the ruling on what counts as evidence outside the reasoner: each tool output becomes a card checkable against the raw input, a checker that sees only the input and the cards decides admission, and the solver answers from admitted cards alone, with no training. On fundus glaucoma screening, chest X-ray pneumonia classification and medical question answering it reaches the highest accuracy among models of comparable scale and significantly outperforms tool-using agents and multi-agent systems reading the same cards.

You’re all caught up