paper-with-me

Papers

ToolSpectrum : Towards Personalized Tool Utilization for Large Language Models

2025-05-19 · Zihao Cheng, Hongru Wang, Zeming Liu, Yuhang Guo, Yuanfang Guo, Yunhong Wang, Haifeng Wang

While integrating external tools into large language models (LLMs) enhances their ability to access real-time information and domain-specific services, existing approaches focus narrowly on functional tool selection following user instructions, overlooking the context-aware personalization in tool selection. This oversight leads to suboptimal user satisfaction and inefficient tool utilization, particularly when overlapping toolsets require nuanced selection based on contextual factors. To bridge this gap, we introduce ToolSpectrum, a benchmark designed to evaluate LLMs' capabilities in personalized tool utilization. Specifically, we formalize two key dimensions of personalization, user profile and environmental factors, and analyze their individual and synergistic impacts on tool utilization. Through extensive experiments on ToolSpectrum, we demonstrate that personalized tool utilization significantly improves user experience across diverse scenarios. However, even state-of-the-art LLMs exhibit the limited ability to reason jointly about user profiles and environmental factors, often prioritizing one dimension at the expense of the other. Our findings underscore the necessity of context-aware personalization in tool-augmented LLMs and reveal critical limitations for current models. Our data and code are available at https://github.com/Chengziha0/ToolSpectrum.

📄 PDF Abstract BibTeX arXiv:2505.13176

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity

2025-03-02 · Yupu Hao, Pengfei Cao, Zhuoran Jin, Huanxuan Liao 외

Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. However, most of the current benchmarks primarily focus on either per…

Text Generation

Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance

2025-05-22 · Taeyoon Kwon, Dongwook Choi, Sunghwan Kim, Hyojun Kim 외

Embodied agents empowered by large language models (LLMs) have shown strong performance in household object rearrangement tasks. However, these tasks primarily focus on single-turn interactions with simplified instructio…

ObjectObject Rearrangement

How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants

2026-01-23 · Xueyang Feng, Weinan Gan, Xu Chen, Quanyu Dai 외 arxiv

Large language model (LLM)-powered assistants have recently integrated memory mechanisms that record user preferences, leading to more personalized and user-aligned responses. However, irrelevant personalized memories ar…

PEToolLLM: Towards Personalized Tool Learning in Large Language Models

2025-02-26 · Qiancheng Xu, Yongqi Li, Heming Xia, Fan Liu 외

Tool learning has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools. Existing tool learning studies primarily focus on the general-purpose tool-use capability, w…

T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step

2023-12-21 · Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu 외

Large language models (LLM) have achieved remarkable performance on various NLP tasks and are augmented by tools for broader applications. Yet, how to evaluate and analyze the tool-utilization capability of LLMs is still…

Instruction FollowingRetrieval