潜在偏好建模用于跨会话个性化工具调用
Latent Preference Modeling for Multi-Session Personalized Tool Calling
AI总结：
本文提出MPT基准和PRefine方法，通过生成-验证-细化循环提升工具调用准确性，仅用1.24%的token实现稳健的个性化。
摘要：
用户在请求LLM代理时常省略关键细节，导致工具调用输入不完整。为此，本文引入包含265个多会话对话的MPT基准，涵盖偏好回忆、诱导和转移三个挑战。提出PRefine方法，通过生成-验证-细化循环提取历史约束，仅用1.24%的token提升准确性，表明代理系统中的稳健个性化依赖于捕捉用户选择背后原因的记忆，而非选择本身。
英文摘要：
Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental challenge for tool-augmented agents, as API execution typically requires complete arguments, highlighting the need for personalized tool calling. To study this problem in a more realistic setup, we present Multi-Session Personalized Tool Calling (MPT), a benchmark comprising 4,695 instances over 459 multi-session interaction histories that cover three challenges: Preference Recall, Induction, and Transfer. We further propose PRefine, a test-time memory method that maintains the user's latent preference as a textual hypothesis revised through a generate-verify-refine loop. Across five LLMs, existing memory systems underperform full-history prompting; PRefine outperforms all baselines and alone surpasses it on Preference Transfer. These results indicate that memory for personalized agents must abstract behavior into preferences, rather than simply archive it.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
