Who May Overrule the Agent? Evidence-Gated Authority in LLM Review Institutions

The paper investigates how a reviewer in multi‑agent language‑model systems can be authorized to override an upstream agent’s decision. It compares unrestricted override authority with an evidence‑gated approach that requires a valid record of a binding‑constraint violation and a compliant repair before replacement is allowed. Experiments on two open‑weight models across 96 spatial‑policy tasks show that the evidence gate sharply reduces corruption of correct proposals while largely preserving legitimate repairs, though the effectiveness varies with reviewer transitions and upstream states.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• benchmarks