# LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation

Source: [LifeSim: Long-Horizon User Life Simulator for Personalized Assistant Evaluation](<https://www.sota2.com/research/paper/69b39a320636e5bf4afbcc8e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-14T05:00:10.861Z

Authors: Feiyu Duan, Xuanjing Huang, Zhongyu Wei

Published: 2026-03-12T16:49:34.000Z

## Abstract

The rapid advancement of large language models (LLMs) has accelerated progress toward universal AI assistants. However, existing benchmarks for personalized assistants remain misaligned with real-world user-assistant interactions, failing to capture the complexity of external contexts and users' cognitive states. To bridge this gap, we propose LifeSim, a user simulator that models user cognition through the Belief-Desire-Intention (BDI) model within physical environments for coherent life trajectories generation, and simulates intention-driven user interactive behaviors. Based on LifeSim, we introduce LifeSim-Eval, a comprehensive benchmark for multi-scenario, long-horizon personalized assistance. LifeSim-Eval covers 8 life domains and 1,200 diverse scenarios, and adopts a multi-turn interactive method to assess models' abilities to complete explicit and implicit intentions, recover user profiles, and produce high-quality responses. Under both single-scenario and long-horizon settings, our experiments reveal that current LLMs face significant limitations in handling implicit intention and long-term user preference modeling.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Behavioral Dialogue Evaluation on LifeSim (test)](<https://www.sota2.com/research/sota/behavioral-dialogue-evaluation-on-lifesim-test.md>): Behavioral Dialogue Evaluation; LifeSim (test); Proactive Inquiry: not recorded.

- [Environment Alignment on LifeSim](<https://www.sota2.com/research/sota/environment-alignment-on-lifesim.md>): Environment Alignment; LifeSim; Environment Alignment: not recorded.

- [Personalized Assistant Interaction on LifeSim-Eval Single-Scenario](<https://www.sota2.com/research/sota/personalized-assistant-interaction-on-lifesim-eval-single-scenario.md>): Personalized Assistant Interaction; LifeSim-Eval Single-Scenario; Explicit Intent Recognition: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.12152>)

[PDF](<https://arxiv.org/pdf/2603.12152.pdf>)
