Persona-Guided LLM Agents for Task-Oriented Dialogue

基于人格引导的大语言模型任务导向对话智能体

Abstract: Prior work has shown that large language models (LLMs) can express diverse personality traits in open-ended text generation. However, it remains unclear whether they can do so in a goal-directed dialogue without compromising task completion, and whether adapting to the user’s personality improves the interaction quality.

摘要： 先前的研究表明，大语言模型（LLMs）在开放式文本生成中能够表现出多样的人格特质。然而，目前尚不清楚它们是否能在不影响任务完成的情况下，在目标导向的对话中做到这一点，以及适应用户的人格是否能提高交互质量。

We study these questions in task-oriented dialogue (TOD), where a system helps a user accomplish a goal via multi-turn interaction. We build a training-free framework that simulates a TOD interaction between two LLMs: a user agent that exhibits a target personality and a system agent that adapts to the user while completing the task.

我们在任务导向对话（TOD）的背景下研究了这些问题，即系统通过多轮交互帮助用户实现目标。我们构建了一个无需训练的框架，模拟了两个大语言模型之间的 TOD 交互：一个表现出特定人格的用户智能体，以及一个在完成任务的同时适应用户的系统智能体。

To isolate the effect of adaptation, we vary how much the system knows about the user’s personality across three conditions. In Neutral, the system receives no personality information. In Try, it infers the personality from dialogue cues. In Oracle, it is given the personality explicitly.

为了隔离适应性的影响，我们在三种条件下改变了系统对用户人格的了解程度。在“中立”（Neutral）条件下，系统不接收任何人格信息；在“尝试”（Try）条件下，系统通过对话线索推断人格；在“预言”（Oracle）条件下，系统被明确告知人格信息。

We evaluate GPT-4o, Qwen3-Next-80B, and Gemini 2.0 Flash on Hotel and Restaurant dialogues from the Schema-Guided Dialogue (SGD) dataset, across the Big Five traits and their opposite poles. We find that the user agent can express personality while the system maintains strong task performance, although some traits are realized far less reliably than others.

我们使用 Schema-Guided Dialogue (SGD) 数据集中的酒店和餐厅对话，对 GPT-4o、Qwen3-Next-80B 和 Gemini 2.0 Flash 进行了评估，涵盖了“大五人格”特质及其对立面。我们发现，用户智能体能够表达人格，同时系统也能保持强大的任务执行性能，尽管某些特质的实现可靠性远低于其他特质。

Adapting to the user’s personality improves constraint satisfaction, inform rate, and user satisfaction, but lowers truthfulness, revealing a trade-off between personalization and task-grounding. Oracle’s gains grow when the target trait is strongly expressed, whereas Try’s gains are largely insensitive to realization strength. Overall, cue-based adaptation in Try best resolves this trade-off and offers a more reliable route to personality-aware TOD without fine-tuning.

适应用户的人格可以提高约束满足度、信息告知率和用户满意度，但会降低真实性，这揭示了个性化与任务基础（task-grounding）之间的权衡。当目标特质表现强烈时，“预言”条件的收益会增加，而“尝试”条件的收益在很大程度上对实现强度不敏感。总体而言，“尝试”条件下的基于线索的适应方式最好地解决了这一权衡，并为实现无需微调的个性化感知 TOD 提供了一条更可靠的途径。