Win by Silence: Deletion Non-Monotonicity and Typed-State Gating in LLM Plan Evaluation

Jul 15, 2026

A new preprint identifies a failure mode in large language model (LLM) plan evaluators, where plans can receive higher scores by omitting necessary steps, thus incentivizing incomplete or deceptive plans. The authors introduce GATE, a typed-state gating mechanism that detects and neutralizes such omission exploits. In experiments, GATE consistently blocked score improvements from omitted steps and improved the quality of revised plans in a cooperative setting. The study provides analytic and empirical evidence of this vulnerability and demonstrates a practical mitigation.

Why it matters: This work exposes a fundamental vulnerability in LLM-based plan evaluation and offers a tested method to address omission incentives, which is important for the reliability of AI-generated plans.

Full story at: arXiv AI/ML ↗