The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world deployment. We identify three key challenges: dynamic task scheduling, active exploration under uncertainty, and continuous learning from experience. To bridge this gap, we introduce \method{}, a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. Unlike traditional benchmarks, \method{} evaluates agents along three dimensions: (1) context-aware scheduling for streaming tasks with varying priorities; (2) prudent information acquisition to reduce hallucination via active exploration; and (3) continuous evolution by distilling generalized strategies from rule-based, dynamically generated tasks. Experiments show that cutting-edge agents have significant deficiencies in dynamic environments, especially in active exploration and continual learning. Our work establishes a framework for assessing agent reliability, shifting evaluation from static tests to realistic, production-oriented scenarios. Our codes are available at https://github.com/KnowledgeXLab/EvoEnv
@article{arxiv.2601.08173,
title = {The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios},
author = {Daocheng Fu and Jianbiao Mei and Rong Wu and Xuemeng Yang and Jia Xu and Ding Wang and Pinlong Cai and Yong Liu and Licheng Wen and Botian Shi},
journal= {arXiv preprint arXiv:2601.08173},
year = {2026}
}