mlsanityData to 14 Oct 2026

TAPS: Tool-Augmented Personalisation via Structured Tagging

arXiv 2506.20409 ↗First posted 25 Jun 2025cs.CLcited by 0

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Recent advancements in tool-augmented large language models have enabled them to interact with external tools, enhancing their ability to perform complex user tasks. However, existing approaches overlook the role of personalisation in guiding tool use. This work investigates how user preferences can be effectively integrated into goal-oriented dialogue agents. Through extensive analysis, we identify key weaknesses in the ability of LLMs to personalise tool use. To this end, we introduce TAPS, a novel solution that enhances personalised tool use by leveraging a structured tagging tool and an uncertainty-based tool detector. TAPS significantly improves the ability of LLMs to incorporate user preferences, achieving the new state-of-the-art for open source models on the NLSI task.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 23 of its 47 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

23 of 47 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark14 May
  2. 2024Learning to Use Tools via Cooperative and Interactive Agents5 Mar
  3. 2024TOOLVERIFIER: Generalization to New Tools via Self-Verification21 Feb
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  5. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
  7. 2022TALM: Tool Augmented Language Models24 May

Other references · 16

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2023Mistral 7Bcited by 3,164
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  6. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  7. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  8. 20242 OLMo 2 Furiouscited by 340
  9. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  10. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 135
  11. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 93
  12. 2023Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Modelscited by 68
4 more
  1. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
  2. 2023ControlLLM: Augment Language Models with Tools by Searching on Graphscited by 59
  3. 2023ToolTalk: Evaluating Tool-Usage in a Conversational Settingcited by 45
  4. 2019Planning for Goal-Oriented Dialogue Systemscited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
  2. 2025ToolSpectrum : Towards Personalized Tool Utilization for Large Language Models
  3. 2025PEToolLLM: Towards Personalized Tool Learning in Large Language Models
  4. 2026Benchmarking LLM Tool-Use in the Wild
  5. 2026Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
  6. 2025PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
  7. 2026AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment
  8. 2026UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs