当"必须"变成"也许"：LLM智能体工作流中的约束弱化

摘要

大语言模型（LLM）智能体通过多角色、多阶段工作流协调复杂任务。上游状态被反复转换为中间语言产物，例如摘要、计划、工单、记忆和交接说明，下游组件据此行动。对于约束行动的状态，仅保留主题内容是不够的：产物可能提及未解决条件，却将其从“执行前必须解决的要求”转变为“仅可能为下一步行动提供参考的信息”。我们将这种行动约束作用称为操作性状态保持。安全阻断器提供了一个受控实例，因为每个源状态都有明确的先决条件、授权、回退方案和执行后果。我们以上游识别正确为条件，改变交接转换方式，并评估仅限于使用所得产物的执行器。在1,296个受控合成情景中，直接交接对照组保留了每一个阻断器，而压缩、计划吸收、收敛、所有权延后和先例替换则反复将约束性状态转变为警告或非约束性考量。常规交接压缩导致100.0%的阻断器失活和54.2%的违禁行动。恢复全部四个状态字段可将保持率提高到100.0%，并将违禁行动降至0.0%。固定产物干预进一步将保持与遏制区分开来：下游验证消除了违禁行动，而产物失活率仍为95.3%。这些结果揭示了信息提取与行动之间的状态传递失败。交接转换可以保留状态内容，同时削弱其对下游行动的约束。语义可用性并不保证操作性保持。

English

Large language model (LLM) agents coordinate complex tasks through multi-role and multi-stage workflows. Upstream state is repeatedly transformed into intermediate language artifacts, such as summaries, plans, tickets, memories, and handoff notes, from which downstream components act. For action-constraining state, topical retention is insufficient: an artifact may mention an unresolved condition while changing it from a requirement that must be resolved before execution into information that may merely inform the next action. We study this action-binding role as operational state preservation. Safety blockers provide a controlled instance because each source state has an explicit prerequisite, authority, fallback, and execution consequence. We condition on correct upstream identification, vary the handoff transformation, and evaluate an executor restricted to the resulting artifact. Across 1,296 controlled synthetic episodes, direct-handoff controls preserve every blocker, whereas compression, plan assimilation, convergence, ownership deferral, and precedent substitution repeatedly turn binding state into caveats or non-binding considerations. Normal handoff compression produces 100.0% deactivation and 54.2% forbidden action. Restoring all four state fields raises preservation to 100.0% and reduces forbidden action to 0.0%. Fixed-artifact interventions further separate preservation from containment: downstream verification eliminates forbidden action while artifact deactivation remains 95.3%. These results identify a state-transmission failure between information extraction and action. Handoff transformations can retain state content while weakening its constraints on downstream action. Semantic availability does not guarantee operational preservation.