Search papers, labs, and topics across Lattice.
PSPA-Bench is introduced as a new benchmark to evaluate personalization in smartphone GUI agents, addressing the limitations of existing benchmarks in capturing user-specific behaviors. The benchmark includes 12,855 personalized instructions across 10 scenarios and 22 apps, along with a structure-aware process evaluation method. Benchmarking 11 state-of-the-art GUI agents reveals poor performance in personalized settings, highlighting the need for reasoning-oriented models, improved perception, and reflection/long-term memory mechanisms.
Today's best smartphone GUI agents stumble when faced with the messy reality of personalized user workflows, achieving only limited success on a new benchmark designed to mimic real-world use.
Smartphone GUI agents execute tasks by operating directly on app interfaces, offering a path to broad capability without deep system integration. However, real-world smartphone use is highly personalized: users adopt diverse workflows and preferences, challenging agents to deliver customized assistance rather than generic solutions. Existing GUI agent benchmarks cannot adequately capture this personalization dimension due to sparse user-specific data and the lack of fine-grained evaluation metrics. To address this gap, we present PSPA-Bench, the benchmark dedicated to evaluating personalization in smartphone GUI agents. PSPA-Bench comprises over 12,855 personalized instructions aligned with real-world user behaviors across 10 representative daily-use scenarios and 22 mobile apps, and introduces a structure-aware process evaluation method that measures agents'personalized capabilities at a fine-grained level. Through PSPA-Bench, we benchmark 11 state-of-the-art GUI agents. Results reveal that current methods perform poorly under personalized settings, with even the strongest agent achieving limited success. Our analysis further highlights three directions for advancing personalized GUI agents: (1) reasoning-oriented models consistently outperform general LLMs, (2) perception remains a simple yet critical capability, and (3) reflection and long-term memory mechanisms are key to improving adaptation. Together, these findings establish PSPA-Bench as a foundation for systematic study and future progress in personalized GUI agents.
Tsinghua AI