Latent Preference Modeling for Cross-Session Personalized Tool Calling
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, we introduce MPT, a benchmark comprising 265 multi-session dialogues that cover three challenges: Preference Recall, Preference Induction, and Preference Transfer. We also propose PRefine, a test-time memory-augmented method that represents user preferences as evolving hypotheses. Through a generate--verify--refine loop, it extracts reusable constraints from history and improves tool-calling accuracy while using only 1.24% of the tokens required by full-history prompting. These results indicate that robust personalization in agentic systems depends on memory that captures the reasons behind user choices, not just the choices themselves.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation
Predicting the next interaction of a short-term interaction session is a challenging task in session-based recommendation. Almost all existing works rely on item transition patterns, and neglect the impact of user histor…
Graph Neural NetworkSession-Based RecommendationsHyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization
Personalized language models aim to adapt responses to individual users, whose preferences are often latent and revealed gradually through interaction. Existing training-free methods rely on stored histories or retrieved…
Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search
The future of conversational agents will provide users with personalized information responses. However, a significant challenge in developing models is the lack of large-scale dialogue datasets that span multiple sessio…
Conversational SearchResponse GenerationEvolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation
Session-based recommendation (SBR) aims to predict the user next action based on the ongoing sessions. Recently, there has been an increasing interest in modeling the user preference evolution to capture the fine-grained…
Session-Based RecommendationsMemoCRS: Memory-enhanced Sequential Conversational Recommender Systems with Large Language Models
Conversational recommender systems (CRSs) aim to capture user preferences and provide personalized recommendations through multi-round natural language dialogues. However, most existing CRS models mainly focus on dialogu…
Recommendation Systems