AI Agents: Evolution, Architecture, and Real-World Applications
It provides a comprehensive overview for researchers and practitioners, but is incremental as it synthesizes existing knowledge without introducing new methods or data.
This paper reviews the evolution and architecture of AI agents, from rule-based systems to modern integrations with large language models, and proposes a holistic evaluation framework to address limitations in current benchmarks.
This paper examines the evolution, architecture, and practical applications of AI agents from their early, rule-based incarnations to modern sophisticated systems that integrate large language models with dedicated modules for perception, planning, and tool use. Emphasizing both theoretical foundations and real-world deployments, the paper reviews key agent paradigms, discusses limitations of current evaluation benchmarks, and proposes a holistic evaluation framework that balances task effectiveness, efficiency, robustness, and safety. Applications across enterprise, personal assistance, and specialized domains are analyzed, with insights into future research directions for more resilient and adaptive AI agent systems.