Latent Preference Modeling for Cross-Session Personalized Tool Calling

• URL: http://arxiv.org/abs/2604.17886v1
• Date: Mon, 20 Apr 2026 06:57:50 GMT
• Title: Latent Preference Modeling for Cross-Session Personalized Tool Calling
• Abstract summary: We introduce MPT, a benchmark comprising 265 multi-session dialogues that cover three challenges: Preference Recall, Preference Induction, and Preference Transfer.<n>We also propose PRefine, a test-time memory-augmented method that represents user preferences as evolving hypotheses.<n>These results indicate that robust personalization in agentic systems depends on memory that captures the reasons behind user choices, not just the choices themselves.
• Score: 9.4096596518028
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs [23.563695173602536]
  UserToolBench is a benchmark for personalized decision making in tool-use LLMs.<n>It tests whether a model can infer latent user preferences from interaction history.<n>It includes 10 user profiles, 36 tool sets, 1,065 turns, 170 unique tools, and evaluation-focused task types.
  arXiv  Detail & Related papers  (2026-08-10T09:32:38Z)
• APeB: Benchmarking Personalization Ability of Large Language Model Agents [17.77241512443464]
  LLM-powered agents struggle with personalization when users issue raw, underspecified queries.<n>Existing benchmarks rarely test this capability, as they often rely on user-refined queries or simplified histories.<n>We introduce personalized product search (PPS), a testbed for agentic personalization under raw queries and diverse histories.
  arXiv  Detail & Related papers  (2026-07-03T10:03:35Z)
• Sparse Personalized Text Generation with Multi-Trajectory Reasoning [95.19317487799292]
  PAT (Personalization with Aligned Trajectories) is a reasoning framework for cold-start LLM personalization.<n>It first retrieves information along two complementary trajectories: writing-style cues from stylistically similar users and topic-specific context from preference-aligned users.<n>It then employs a reinforcement learning-based, iterative dual-reasoning mechanism that enables the LLM to jointly refine and integrate these signals.
  arXiv  Detail & Related papers  (2026-04-27T20:58:49Z)
• KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation [72.01173512175531]
  KnowU-Bench is an online benchmark for personalized mobile agents.<n>It covers 42 general GUI tasks, 86 personalized tasks, and 64 proactive tasks.<n>Our experiments reveal a striking degradation: agents that excel at explicit task execution fall below 50% under vague instructions.
  arXiv  Detail & Related papers  (2026-04-09T16:50:50Z)
• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation [63.74915464611075]
  RecThinker is an agentic framework for tool-augmented reasoning in recommendation.<n>We develop a suite of specialized tools for RecThinker, enabling the model to acquire user item-side and collaborative information.
  arXiv  Detail & Related papers  (2026-03-10T16:07:17Z)
• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents [55.27061195244624]
  We formalize over-personalization into three types: Irrelevance, Repetition, and Sycophancy.<n>Agents tend to retrieve and over-attend to user memories even when unnecessary.<n>Our work takes an initial step toward more controllable and appropriate personalization in memory-augmented dialogue systems.
  arXiv  Detail & Related papers  (2026-01-20T08:27:13Z)
• PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization [4.624026598342624]
  We propose PrLM, a reinforcement learning framework that trains LLMs to explicitly reason over retrieved user profiles.<n>PrLM effectively learns from user responses without requiring annotated reasoning paths.<n>Experiments on three personalized text generation datasets show that PrLM outperforms existing methods.
  arXiv  Detail & Related papers  (2025-08-10T13:37:26Z)
• Advancing and Benchmarking Personalized Tool Invocation for LLMs [66.39214525683425]
  We introduce the concept of Personalized Tool Invocation and define two key tasks: Tool Preference and Profile-dependent Query.<n>To tackle these challenges, we propose PTool, a data synthesis framework designed for personalized tool invocation.<n>We construct textbfPTBench, the first benchmark for evaluating personalized tool invocation.
  arXiv  Detail & Related papers  (2025-05-07T02:25:20Z)
• Beyond the Binary: Capturing Diverse Preferences With Reward Regularization [15.518838657050173]
  We argue that this reliance on binary choices does not capture the broader, aggregate preferences of the target user in real-world tasks.<n>We introduce a simple yet effective method that augments existing binary preference datasets with synthetic preference judgments to estimate potential user disagreement.
  arXiv  Detail & Related papers  (2024-12-05T02:35:46Z)
• Hallucination-minimized Data-to-answer Framework for Financial Decision-makers [1.3781777926017094]
  Large Language Models (LLMs) have been applied to build several automation and personalized question-answering prototypes so far. We present a novel Langchain-based framework that transforms data tables into hierarchical textual data chunks to enable a wide variety of actionable question answering.
  arXiv  Detail & Related papers  (2023-11-09T22:53:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.