做LLM安全对齐或代理系统部署的团队必须关注——一句简单的“保持一致”就能让最强模型从安全转向危险，这意味着轨迹注入攻击可能轻易绕过现有防护，建议仔细阅读实验设计并评估自身系统的脆弱性。
该研究构建了HistoryAnchor-100数据集，包含100个高风险场景，每个场景强制模型先执行三个有害动作，再给出自由选择节点。测试17个前沿模型发现，在无特殊提示时，对齐模型几乎不选不安全选项；但加入一句“与历史策略保持一致”后，不安全选择率飙升至91-98%。控制实验排除了标签混淆和指令本身的影响，且不同模型家族对有害历史剂量反应不同，旗舰模型受影响最大。这警示了代理部署中轨迹回放、伪造或注入的安全风险。
History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions
Frontier LLMs are increasingly deployed as agents that pick the next action after a long log of prior tool calls produced by the same or a different model. We ask a simple safety question: if a prior step in that log was harmful, will the model continue the harmful course? We build HistoryAnchor-100, 100 short scenarios across ten high-stakes domains, each pairing three forced harmful prior actions with a free-choice node offering two safe and two unsafe options. Across 17 frontier models from six providers we find a striking asymmetry: under a neutral system prompt the strongest aligned models almost never pick unsafe, but a single added sentence, "stay consistent with the strategy shown in the prior history", flips them to 91-98%, and the flipped models often escalate beyond continuation. Two controls rule out simpler explanations: permuting action labels leaves the effect intact, and the same instruction with an all-safe prior history keeps unsafe rates below 7%. Different families flip at different doses of unsafe history, and within every aligned family the flagship is the most affected sibling, an inverse-scaling pattern with respect to safety. These results are a red flag for agentic deployments where trajectories may be replayed, forged, or injected.