构建可完全委托的旅行规划智能体，提升个性化与自适应能力。
Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning
- 提出APEC行为准则，从准确性、主动性、效率和可信度四方面评估智能体行为
- 基于合成数据训练的APEC-Travel在规则指标上超越基线20.7%，评分提升9.1%
- 适合关注智能体可信赖性与人性化交互的研究者与开发者
未来大模型智能体将如何应用？现有研究多聚焦于特定任务性能提升，本文提出全委托视角：智能体接管人类日常决策，满足个性化需求并适应动态环境。为此，需同时评估智能体成果（结果评价）与实现过程（流程评价）。我们提出APEC智能体守则，包含准确性、主动性、效率与可信度四项标准。为验证其有效性，我们构建了基于合成数据的APEC-Travel旅行规划智能体，数据由Llama3.1-405B-Instruct生成，涵盖多样化用户人格特征。通过迭代微调使智能体遵循APEC守则，其在规则指标上比基线高出20.7%，在LLM作为裁判的评分中提升9.1%。
原文摘要 · Abstract (English)
How are LLM-based agents used in the future? While many of the existing work on agents has focused on improving the performance of a specific family of objective and challenging tasks, in this work, we take a different perspective by thinking about full delegation: agents take over humans' routine decision-making processes and are trusted by humans to find solutions that fit people's personalized needs and are adaptive to ever-changing context. In order to achieve such a goal, the behavior of the agents, i.e., agentic behaviors, should be evaluated not only on their achievements (i.e., outcome evaluation), but also how they achieved that (i.e., procedure evaluation). For this, we propose APEC Agent Constitution, a list of criteria that an agent should follow for good agentic behaviors, including Accuracy, Proactivity, Efficiency and Credibility. To verify whether APEC aligns with human preferences, we develop APEC-Travel, a travel planning agent that proactively extracts hidden personalized needs via multi-round dialog with travelers. APEC-Travel is constructed purely from synthetic data generated by Llama3.1-405B-Instruct with a diverse set of travelers' persona to simulate rich distribution of dialogs. Iteratively fine-tuned to follow APEC Agent Constitution, APEC-Travel surpasses baselines by 20.7% on rule-based metrics and 9.1% on LLM-as-a-Judge scores across the constitution axes.
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。