任务故事比角色设定更能影响大模型行为，揭示了叙事先验的作用。
The Story Shapes the Agent: Narrative Priors in LLM Behavior
- 通过相同结构但不同故事的任务对比，发现叙事框架主导行为模式。
- 叙事因素解释的行为差异是角色设定的5到31倍，且与任务成功负相关。
- 提升跨故事一致性需基于具体动作描述，而非抽象角色设定。
角色提示广泛用于引导大模型智能体行为，但任务的叙事框架可能比分配的角色更具影响力。我们通过结构同构设计了三个文本调查游戏：疾病调查、IT故障排查和谋杀谜案，三者具有相同的动作空间、阶段推进和资源约束，仅任务叙事不同。在跨越3个模型和10个角色的1890次实验中，我们识别出叙事先验——由任务故事框架激活的系统性行为倾向，与决策结构无关。叙事先验解释的行为方差是角色设定的5至31倍，且在三种领域中有两种与任务成功呈负相关。角色效应跨叙事传递的现象源于行为锚点：其语言直接映射到共享动作的描述。因果干预验证了这一点：移除高传递角色中的锚点词后，跨叙事一致性下降95%。该框架还推广至第四种未见过的叙事，并提出一种提升跨叙事迁移能力的角色选择方法。结果表明，真正能适应叙事变化的模型行为应基于具体动作，而非抽象描述。
原文摘要 · Abstract (English)
Persona prompting is widely used to steer LLM agent behavior, yet the narrative framing of a task can matter more than the assigned persona. We isolate this effect through structural isomorphism, constructing three text-based investigation games that share the same action space, stage progression, and resource constraints while varying only task narrative: disease investigation, IT troubleshooting, and murder mystery. Across 1,890 sessions spanning 3 models and 10 personas, we identify narrative priors: systematic action tendencies activated by a task's story framing, independent of its decision structure. Narrative priors explain 5-31x more behavioral variance than persona, are consistent across model architectures, and in two of three domains are negatively associated with task success. Persona effects that do transfer across narratives arise from behavioral anchors, persona descriptions whose language maps directly onto shared actions. Causal interventions confirm this: removing anchor words from a high-transfer persona reduces cross-narrative consistency by 95%. Our framework also generalizes to a held-out fourth narrative and yields a persona-selection method that improves cross-narrative transfer. These results suggest that LLM behavior that survives narrative changes should be grounded in concrete actions rather than abstract descriptions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。