A Large-Scale Empirical Study of Quality Assurance Practices and Gaps in AI Agents

RESUMO

Large language model (LLM)-based agents are increasingly used across software engineering, web automation, research, and productivity applications. Their integration of planning, memory, tool use, code execution, and external interactions enables greater autonomy but also introduces new reliability, safety, and security risks. We present a large-scale empirical study of quality assurance (QA) practices in 157 open-source LLM-based agent projects with at least 100 GitHub stars. We analyze documentation, source code, configurations, and tests to characterize QA execution surfaces, safeguards, testing artifacts, risk scenarios, and recurring gaps. We find that current QA primarily focuses on basic functionality and high-risk actions, while coverage remains fragmented. Safeguards are inconsistently applied across equivalent execution routes, and tests rarely examine boundary, adversarial, or multi-step tool-use failures. Identified risks are seldom translated into end-to-end QA checks. These findings highlight the need to move beyond feature-level testing toward systematic end-to-end validation ensuring agent workflows remain within intended boundaries when interacting with untrusted inputs, tools, persistent state, and APIs.