Skip to main content
Search

# nrepair

1 related articles

Subscribe to updates
  1. arXiv

    Agents Fall Back Past the Line: nrepair Cuts Boundary-Crossing Actions by Up to 76% Across Four Models

    Large language model agents often switch to a substitute tool after an ordinary tool error, but the same fallback crosses an action boundary when the target's state differs, as when a forced push deletes another author's commits. Across 304 scenarios covering 55 real CVEs, four mainstream models crossed the boundary in up to 96.8% of risky scenarios, while three mainstream mitigations stopped violations only by also stopping legitimate recoveries. nrepair instead scores the agent's context at each substitute call and, on a trigger, withholds the call once and returns the decision to the agent, lowering the violation rate on Luna from 67.5% to 16.2% while normal success on Qwen and Gemma falls only slightly.

You’re all caught up