发表机构
Beijing Qiyuan Technology Co., Ltd.（北京奇源科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究在蒸馏-验证-迁移协议下探究提示侧智能体剧本的可迁移性，在ALFWorld、TAU2-Bench、XBench-DeepSearch等基准上测试发现其为有条件的冷启动选项，需目标侧验证相关指标。
AI 中文摘要
提示侧剧本无需重新训练即可提升使用工具的语言智能体的性能，但其在源设置之外的可迁移性尚不明确。我们在共享的蒸馏-验证-迁移协议下研究冻结剧本的迁移。在ALFWorld上，在受控贪心解码下迁移是有益的，且在一项接近预算匹配的比较中，蒸馏指导优于5个固定演示。在TAU2-Bench上，预先指定的总体对比支持适度的平均匹配域优势，但全局Holm校正在135个路线级效应中仅保留1个；剩余网格提供了兼容性敏感异质性的描述性证据。在XBench-DeepSearch上，一种人工制品-运行时配对在保留有用的首次尝试启发式的同时，在上下文-运行时偏移后产生重复查询、延迟终止和大幅成本膨胀。在所有基准上，迁移的和目标衍生的剧本都需要在目标侧验证成功、终止、协议兼容性和成本。因此，冻结迁移是有条件的冷启动选项，而非默认复用策略或优于目标侧重新蒸馏的普遍优选方案。
英文摘要
Prompt-side playbooks can improve tool-using language agents without retraining, but their portability beyond the source setting is unclear. We study frozen playbook transfer under a shared distill--validate--transfer protocol. On ALFWorld, transfer is beneficial under controlled greedy decoding and, in one near-budget-matched comparison, distilled guidance outperforms five fixed demonstrations. On TAU2-Bench, a prespecified aggregate contrast supports a modest average matched-domain advantage, but global Holm correction retains only one of 135 route-level effects; the remaining grid provides descriptive evidence of compatibility-sensitive heterogeneity. On XBench-DeepSearch, one artifact--runtime pairing preserves useful first-try heuristics while producing repeated queries, delayed stopping, and substantial cost inflation after a context-runtime shift. Across benchmarks, transferred and target-derived playbooks both require target-side validation of success, termination, protocol compatibility, and cost. Frozen transfer is therefore a conditional cold-start option, not a reuse-by-default strategy or a universally preferable alternative to target-side redistillation.
