Lune

ACL Findings2025

ToolSpectrum: Towards Personalized Tool Utilization for Large Language Models

Zihao Cheng, Hongru Wang, Zeming Liu, Yuhang Guo, Yuanfang Guo, Yunhong Wang, Haifeng Wang

Abstract

While integrating external tools into large language models (LLMs) enhances their ability to access real-time information and domainspecific services, existing approaches focus narrowly on functional tool selection following user instructions, overlooking the contextaware 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-theart 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 in current models. Our data and code are available at https://github.com/ BUAA-IRIP-LLM/ToolSpectrum.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Large Language Models are Zero-Shot Reasoners cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • AgentBench: Evaluating LLMs as Agents cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • AgentBench: Evaluating LLMs as Agents cites WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
  • ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. In-the-Flow Agentic System Optimization for Effective Planning and Tool UseZhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu et al.ICLR 2026 · 65 citations
  2. Mem²Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience DistillationZihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang et al.ACL 2026 · 4 citations

Builds on29

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
  3. WebShop: Towards Scalable Real-World Web Interaction with Grounded Language AgentsShunyu Yao, Howard Chen, John Yang, Karthik NarasimhanNeurIPS 2022 · 1,477 citations
  4. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsYujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu et al.ICLR 2024 · 1,469 citations
  5. AgentBench: Evaluating LLMs as AgentsXiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu et al.ICLR 2024 · 748 citations

Related papers

  1. ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware FilteringMarianne Menglin Liu, Daniel Garcia, Fjona Parllaku, Vikas Upadhyay et al.ACL 2026 · 11 citations
  2. PEToolLLM: Towards Personalized Tool Learning in Large Language ModelsQiancheng Xu, Yongqi Li, Heming Xia, Fan Liu et al.ACL Findings 2025
  3. SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMsHongfei Xia, Hongru Wang, Zeming Liu, Qian Yu et al.EMNLP Findings 2025 · 1 citation
  4. MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to UseYue Huang, Jiawen Shi, Yuan Li, Chenrui Fan et al.ICLR 2024 · 188 citations
  5. Enhancing Tool Retrieval with Iterative Feedback from Large Language ModelsQiancheng Xu, Yongqi Li, Heming Xia, Wenjie LiEMNLP Findings 2024 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines