# SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

arXiv: https://arxiv.org/abs/2608.10692 · HTML: https://mlsanity.com/paper/2608.10692/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 23 of 23)

- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration](https://mlsanity.com/paper/2406.01014/) (2024)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents](https://mlsanity.com/paper/2410.24024/) (2024)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [AutoGLM: Autonomous Foundation Agents for GUIs](https://mlsanity.com/paper/2411.00820/) (2024)
- [SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation](https://mlsanity.com/paper/2410.15164/) (2024)
- [ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use](https://mlsanity.com/paper/2501.02506/) (2025)
- [Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments](https://mlsanity.com/paper/2602.11964/) (2026)
- [LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects](https://mlsanity.com/paper/2504.19838/) (2025)
- [Large Language Model Instruction Following: A Survey of Progresses and Challenges](https://mlsanity.com/paper/2303.10475/) (2023)
- [FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models](https://mlsanity.com/paper/2402.14116/) (2024)
- [Intelligent Virtual Assistants with LLM-based Process Automation](https://mlsanity.com/paper/2312.06677/) (2023)
- [Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis](https://mlsanity.com/paper/2506.01262/) (2025)
- [Mind the Third Eye! Benchmarking Privacy Awareness in MLLM-powered Smartphone Agents](https://mlsanity.com/paper/2508.19493/) (2025)
- [Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation](https://mlsanity.com/paper/2505.11683/) (2025)
- [Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models](https://mlsanity.com/paper/2510.17922/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple applications (apps) to complete user instructions. However, due to the lack of dedicated benchmarks, their capabilities remain poorly understood. To address this gap, we introduce SPIEval, a human-curated benchmark grounded in five cognitive capabilities (i.e., reasoning, disambiguation, integration, preference inference, and multi-intent decomposition). SPIEval comprises 250 tasks spanning 4,335 personal records distributed across 10 apps and supports multi-turn interaction through 21 tools. Analysis shows that the benchmark exhibits diverse scenarios, challenging tasks, scattered information, controllable environments, and verifiable outcomes. We evaluate nine representative LLMs and find substantial room for improvement. The best-performing model, GPT-5.5 (xhigh), achieves only 57.3% accuracy, while the weakest achieves just 16.4%. Further analysis reveals that 79% of failures stem from inaccurate information localization, as LLMs often commit to plausible but incorrect information instead of continuing retrieval for verification. We also find that fewer than 2% of retrieval actions employ advanced search methods and observe substantial variation in search efficiency across models. These findings expose fundamental limitations of current LLM-based mobile assistants and motivate future research in this direction. Data and code are available at https://huggingface.co/datasets/Junjie-Ye/SPIEval.