A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908491863556096 |
|---|---|
| author | Qu, Xiaodong Damoah, Andrews Sherwood, Joshua Liu, Peiyan Jin, Christian Shun Chen, Lulu Shen, Minjie Aleisa, Nawwaf Hou, Zeyuan Zhang, Chenyu Gao, Lifu Li, Yanshu Yang, Qikai Wang, Qun De Souza, Cristabelle |
| author_facet | Qu, Xiaodong Damoah, Andrews Sherwood, Joshua Liu, Peiyan Jin, Christian Shun Chen, Lulu Shen, Minjie Aleisa, Nawwaf Hou, Zeyuan Zhang, Chenyu Gao, Lifu Li, Yanshu Yang, Qikai Wang, Qun De Souza, Cristabelle |
| contents | Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data, advances in deep learning, reinforcement learning, and multi-agent coordination have accelerated this transformation. Yet, designing and deploying unified AI agents that seamlessly integrate cognition, planning, and interaction remains a grand challenge. In this review, we systematically examine the architectural principles, foundational components, and emergent paradigms that define the landscape of contemporary AI agents. We synthesize insights from cognitive science-inspired models, hierarchical reinforcement learning frameworks, and large language model-based reasoning. Moreover, we discuss the pressing ethical, safety, and interpretability concerns associated with deploying these agents in real-world scenarios. By highlighting major breakthroughs, persistent challenges, and promising research directions, this review aims to guide the next generation of AI agent systems toward more robust, adaptable, and trustworthy autonomous intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11957 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond Qu, Xiaodong Damoah, Andrews Sherwood, Joshua Liu, Peiyan Jin, Christian Shun Chen, Lulu Shen, Minjie Aleisa, Nawwaf Hou, Zeyuan Zhang, Chenyu Gao, Lifu Li, Yanshu Yang, Qikai Wang, Qun De Souza, Cristabelle Multiagent Systems Artificial Intelligence Machine Learning Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data, advances in deep learning, reinforcement learning, and multi-agent coordination have accelerated this transformation. Yet, designing and deploying unified AI agents that seamlessly integrate cognition, planning, and interaction remains a grand challenge. In this review, we systematically examine the architectural principles, foundational components, and emergent paradigms that define the landscape of contemporary AI agents. We synthesize insights from cognitive science-inspired models, hierarchical reinforcement learning frameworks, and large language model-based reasoning. Moreover, we discuss the pressing ethical, safety, and interpretability concerns associated with deploying these agents in real-world scenarios. By highlighting major breakthroughs, persistent challenges, and promising research directions, this review aims to guide the next generation of AI agent systems toward more robust, adaptable, and trustworthy autonomous intelligence. |
| title | A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond |
| topic | Multiagent Systems Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2508.11957 |