Latent Preference Modeling for Multi-Session Personalized Tool Calling
On the map: LLM agents and tool use → Agent memory systems
Abstract (arXiv)
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 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 often fail to improve on 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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 40 of its 56 references that are in the map. First posted on arXiv 20 Apr 2026.
Builds on
40 of 56 references.
Closest ancestors · 6
Same direction, newest first
- 2026Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory4 Mar
- 2026SimpleMem: Efficient Lifelong Memory for LLM Agents5 Jan
- 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory7 Dec
- 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory25 Nov
- 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
- 2025A-MEM: Agentic Memory for LLM Agents17 Feb
Other references · 34
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
- 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
- 2024Large Language Models: A Surveycited by 525
- 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
- 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
- 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
- 2020SLURP: A Spoken Language Understanding Resource Packagecited by 198
22 more
- 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 178
- 2018Towards Deep Conversational Recommendationscited by 176
- 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 148
- 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 140
- 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 138
- 2020Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusioncited by 122
- 2019Towards Knowledge-Based Recommender Dialog Systemcited by 113
- 2020Towards Topic-Guided Conversational Recommender Systemcited by 94
- 2020INSPIRED: Toward Sociable Recommendation Dialog Systemscited by 93
- 2017Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systemscited by 85
- 2024GTA: A Benchmark for General Tool Agentscited by 77
- 2020CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Datasetcited by 66
- 2021DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendationcited by 46
- 2020RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modelingcited by 41
- 2025A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directionscited by 34
- 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Modelscited by 34
- 2025CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactionscited by 22
- 2025HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devicescited by 15
- 2023WHAT, WHEN, and HOW to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialoguecited by 10
- 2024FunctionChat-Bench: Comprehensive Evaluation of Language Models' Generative Capabilities in Korean Tool-use Dialogscited by 8
- 2025Advancing and Benchmarking Personalized Tool Invocation for LLMscited by 8
- 2023Interpreting User Requests in the Context of Natural Language Standing Instructionscited by 5
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents
- 2026UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs
- 2026User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
- 2026Towards Natural Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions
- 2025PersonaAgent: Bridging Memory and Action for Personalized LLM Agents
- 2026PDEU-Bench: Benchmarking the Personalized Planning Lifecycle of Tool-Calling LLM Agents
- 2026Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
- 2026BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs