Next-generation AI must manage vast personal data, diverse tools, and multi-step reasoning, yet most benchmarks remain context-free and single-turn. We present ASTRA-bench (Assistant Skills in Tool-use, Reasoning \& Action-planning), a benchmark that uniquely unifies time-evolving personal context with an interactive toolbox and complex user intents. Our event-driven pipeline generates 2,413 scenarios across four protagonists, grounded in longitudinal life events and annotated by referential, functional, and informational complexity. Evaluation of state-of-the-art models (e.g., Claude-4.5-Opus, DeepSeek-V3.2) reveals significant performance degradation under high-complexity conditions, with argument generation emerging as the primary bottleneck. These findings expose critical limitations in current agents' ability to ground reasoning within messy personal context and orchestrate reliable multi-step plans. We release ASTRA-bench with a full execution environment and evaluation scripts to provide a diagnostic testbed for developing truly context-aware AI assistants.
@article{arxiv.2603.01357,
title = {ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context},
author = {Zidi Xiu and David Q. Sun and Kevin Cheng and Maitrik Patel and Josh Date and Yizhe Zhang and Jiarui Lu and Omar Attia and Raviteja Vemulapalli and Oncel Tuzel and Meng Cao and Samy Bengio},
journal= {arXiv preprint arXiv:2603.01357},
year = {2026}
}