213 lines
11 KiB
BibTeX
213 lines
11 KiB
BibTeX
% THEME 1: Foundations & Architectures of Agentic AI
|
||
|
||
% Comprehensive 2025 survey — dual-paradigm framework (symbolic vs neural)
|
||
@article{abuali2025agentic,
|
||
title={Agentic AI: a comprehensive survey of architectures, applications, and future directions},
|
||
volume={59},
|
||
ISSN={1573-7462},
|
||
url={http://dx.doi.org/10.1007/s10462-025-11422-4},
|
||
DOI={10.1007/s10462-025-11422-4},
|
||
number={1},
|
||
journal={Artificial Intelligence Review},
|
||
publisher={Springer Science and Business Media LLC},
|
||
author={Abou Ali, Mohamad and Dornaika, Fadi and Charafeddine, Jinan},
|
||
year={2025},
|
||
month=Nov
|
||
}
|
||
|
||
% Widely cited foundational survey on LLM-based autonomous agents
|
||
@article{wang2024survey,
|
||
title={A survey on large language model based autonomous agents},
|
||
volume={18},
|
||
ISSN={2095-2236},
|
||
url={http://dx.doi.org/10.1007/s11704-024-40231-1},
|
||
DOI={10.1007/s11704-024-40231-1},
|
||
number={6},
|
||
journal={Frontiers of Computer Science},
|
||
publisher={Springer Science and Business Media LLC},
|
||
author={Wang, Lei and Ma, Chen and Feng, Xueyang and Zhang, Zeyu and Yang, Hao and Zhang, Jingsen and Chen, Zhiyuan and Tang, Jiakai and Chen, Xu and Lin, Yankai and Zhao, Wayne Xin and Wei, Zhewei and Wen, Jirong},
|
||
year={2024},
|
||
month=Mar
|
||
}
|
||
|
||
% Taxonomy: Perception, Brain, Planning, Action, Tools; evaluation framework
|
||
@misc{arunkumar2026architectures,
|
||
title={Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents},
|
||
author={Arunkumar V and Gangadharan G. R. and Rajkumar Buyya},
|
||
year={2026},
|
||
eprint={2601.12560},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.AI},
|
||
url={https://arxiv.org/abs/2601.12560},
|
||
}
|
||
|
||
% Systematic review of CrewAI, LangGraph, AutoGen, MetaGPT
|
||
@misc{derouiche2025frameworks,
|
||
title={Agentic AI Frameworks: Architectures, Protocols, and Design Challenges},
|
||
author={Hana Derouiche and Zaki Brahmi and Haithem Mazeni},
|
||
year={2025},
|
||
eprint={2508.10146},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.AI},
|
||
url={https://arxiv.org/abs/2508.10146},
|
||
}
|
||
|
||
% THEME 2: Multi-Agent Systems & Coordination
|
||
|
||
% ACM TOSEM — literature review on LLM multi-agent SE systems (peer-reviewed journal)
|
||
@article{ishibashi2024multiagent,
|
||
author = {He, Junda and Treude, Christoph and Lo, David},
|
||
title = {LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision, and the Road Ahead},
|
||
year = {2025},
|
||
issue_date = {June 2025},
|
||
publisher = {Association for Computing Machinery},
|
||
address = {New York, NY, USA},
|
||
volume = {34},
|
||
number = {5},
|
||
issn = {1049-331X},
|
||
url = {https://doi.org/10.1145/3712003},
|
||
doi = {10.1145/3712003},
|
||
abstract = {Integrating Large Language Models (LLMs) into autonomous agents marks a significant shift in the research landscape by offering cognitive abilities that are competitive with human planning and reasoning. This article explores the transformative potential of integrating Large Language Models into Multi-Agent (LMA) systems for addressing complex challenges in software engineering (SE). By leveraging the collaborative and specialized abilities of multiple agents, LMA systems enable autonomous problem-solving, improve robustness, and provide scalable solutions for managing the complexity of real-world software projects. In this article, we conduct a systematic review of recent primary studies to map the current landscape of LMA applications across various stages of the software development lifecycle (SDLC). To illustrate current capabilities and limitations, we perform two case studies to demonstrate the effectiveness of state-of-the-art LMA frameworks. Additionally, we identify critical research gaps and propose a comprehensive research agenda focused on enhancing individual agent capabilities and optimizing agent synergy. Our work outlines a forward-looking vision for developing fully autonomous, scalable, and trustworthy LMA systems, laying the foundation for the evolution of Software Engineering 2.0.},
|
||
journal = {ACM Trans. Softw. Eng. Methodol.},
|
||
month = may,
|
||
articleno = {124},
|
||
numpages = {30},
|
||
keywords = {Large Language Models, Autonomous Agents, Multi-Agent Systems, Software Engineering}
|
||
}
|
||
|
||
% IEEE conference — multi-agent LLM environment for software design and refactoring
|
||
@INPROCEEDINGS{ieee2025multiagent,
|
||
author={Rajendran, Vasanth and Besiahgari, Dinesh and Patil, Sachin C. and Chandrashekaraiah, Manjunath and Challagulla, Vishnu},
|
||
booktitle={SoutheastCon 2025},
|
||
title={A Multi-Agent LLM Environment for Software Design and Refactoring: A Conceptual Framework},
|
||
year={2025},
|
||
volume={},
|
||
number={},
|
||
pages={488-493},
|
||
keywords={Software design;Codes;Large language models;Scalability;Software quality;Software systems;Security;Optimization;Software engineering;Software development management;Multi-agent systems;Large Language Models;Software refactoring;Agent specialization;Consensus protocols;Auction mechanisms;Code quality},
|
||
doi={10.1109/SoutheastCon56624.2025.10971563}
|
||
}
|
||
|
||
|
||
|
||
% IEEE/ACM workshop — reference software architecture for LLM-based multi-agent systems
|
||
@INPROCEEDINGS{sallma2025,
|
||
author={Becattini, Marco and Verdecchia, Roberto and Vicario, Enrico},
|
||
booktitle={2025 IEEE/ACM International Workshop New Trends in Software Architecture (SATrends)},
|
||
title={SALLMA: A Software Architecture for LLM-Based Multi-Agent Systems},
|
||
year={2025},
|
||
volume={},
|
||
number={},
|
||
pages={5-8},
|
||
keywords={Structured Query Language;Software architecture;NoSQL databases;Pressing;Market research;Software;Real-time systems;Faces;Multi-agent systems;Python;software architecture;se4ai;llm},
|
||
doi={10.1109/SATrends66715.2025.00006}}
|
||
|
||
|
||
% THEME 3: Software Engineering Applications
|
||
|
||
% Survey of LLM agents across SE tasks: requirements, code gen, design, testing, maintenance
|
||
@misc{jin2024llmagents,
|
||
title={From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future},
|
||
author={Haolin Jin and Linghan Huang and Haipeng Cai and Jun Yan and Bo Li and Huaming Chen},
|
||
year={2025},
|
||
eprint={2408.02479},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.SE},
|
||
url={https://arxiv.org/abs/2408.02479},
|
||
}
|
||
|
||
% 124-paper survey from both SE and agent perspectives (accepted at ACM TOSEM)
|
||
@misc{liu2024llmse,
|
||
title={Large Language Model-Based Agents for Software Engineering: A Survey},
|
||
author={Junwei Liu and Kaixin Wang and Yixuan Chen and Xin Peng and Zhenpeng Chen and Lingming Zhang and Yiling Lou},
|
||
year={2025},
|
||
eprint={2409.02977},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.SE},
|
||
url={https://arxiv.org/abs/2409.02977},
|
||
}
|
||
|
||
% SWE-bench — benchmark for evaluating agents on real GitHub issues (ICLR 2024)
|
||
@misc{jimenez2024swebench,
|
||
title={SWE-bench: Can Language Models Resolve Real-World GitHub Issues?},
|
||
author={Carlos E. Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan},
|
||
year={2024},
|
||
eprint={2310.06770},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.CL},
|
||
url={https://arxiv.org/abs/2310.06770},
|
||
}
|
||
|
||
% THEME 4: Planning, Reasoning & Tool Use
|
||
|
||
% Surveys reasoning, planning, tool-calling patterns across agent architectures
|
||
@misc{masterman2024landscape,
|
||
title={The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey},
|
||
author={Tula Masterman and Sandi Besen and Mason Sawtell and Alex Chao},
|
||
year={2024},
|
||
eprint={2404.11584},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.AI},
|
||
url={https://arxiv.org/abs/2404.11584},
|
||
}
|
||
|
||
% Generative agents — foundational simulation of autonomous agent behaviour (UIST 2023)
|
||
@inproceedings{park2023generative,
|
||
author = {Park, Joon Sung and O'Brien, Joseph and Cai, Carrie Jun and Morris, Meredith Ringel and Liang, Percy and Bernstein, Michael S.},
|
||
title = {Generative Agents: Interactive Simulacra of Human Behavior},
|
||
year = {2023},
|
||
isbn = {9798400701320},
|
||
publisher = {Association for Computing Machinery},
|
||
address = {New York, NY, USA},
|
||
url = {https://doi.org/10.1145/3586183.3606763},
|
||
doi = {10.1145/3586183.3606763},
|
||
abstract = {Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents: computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent’s experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty-five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors. For example, starting with only a single user-specified notion that one agent wants to throw a Valentine’s Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture—observation, planning, and reflection—each contribute critically to the believability of agent behavior. By fusing large language models with computational interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.},
|
||
booktitle = {Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology},
|
||
articleno = {2},
|
||
numpages = {22},
|
||
keywords = {Human-AI interaction, agents, generative AI, large language models},
|
||
location = {San Francisco, CA, USA},
|
||
series = {UIST '23}
|
||
}
|
||
|
||
% -----------------------------------------------
|
||
% Additional references — official framework documentation
|
||
% -----------------------------------------------
|
||
|
||
% LangGraph official documentation — graph-based stateful agent workflows
|
||
@misc{langgraphdocs,
|
||
title={LangGraph Documentation},
|
||
author={{LangChain AI}},
|
||
year={2025},
|
||
url={https://langchain-ai.github.io/langgraph/},
|
||
note={Accessed May 2025}
|
||
}
|
||
|
||
% CrewAI official documentation — role-based multi-agent orchestration framework
|
||
@misc{crewaidocs,
|
||
title={CrewAI Documentation},
|
||
author={{CrewAI Inc.}},
|
||
year={2025},
|
||
url={https://docs.crewai.com/},
|
||
note={Accessed May 2025}
|
||
}
|
||
|
||
% AutoGen official documentation — Microsoft's conversational multi-agent framework
|
||
@misc{autogendocs,
|
||
title={AutoGen Documentation},
|
||
author={{Microsoft Research}},
|
||
year={2025},
|
||
url={https://microsoft.github.io/autogen/},
|
||
note={Accessed May 2025}
|
||
}
|
||
|
||
% AI agentic programming: planning, memory, tool integration, execution monitoring
|
||
@misc{wang2025aiagenticprogrammingsurvey,
|
||
title={AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities},
|
||
author={Huanting Wang and Jingzhi Gong and Huawei Zhang and Jie Xu and Zheng Wang},
|
||
year={2025},
|
||
eprint={2508.11126},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.SE},
|
||
url={https://arxiv.org/abs/2508.11126},
|
||
} |