Frontiers of Large Language Model-Based Agentic Systems - Construction, Efficacy and Safety
Authors: 
Jia He, Reshmi Ghosh, Kabir Walia, Jieqiu Chen, Tushar Dhadiwal, April Hazel, Chandra InguvaAuthors Info & Claims
Jia He, Reshmi Ghosh, Kabir Walia, Jieqiu Chen, Tushar Dhadiwal, April Hazel, Chandra InguvaAuthors Info & ClaimsPages 5526 - 5529
Abstract
"The previous era was about information at your fingertips; I think of the AI era as expertise at your fingertips." - Satya Nadella, CNBC
This tutorial explores Large Language Model (LLM)-based autonomous agents, addressing the lack of comprehensive guides on the topic. It systematically examines key components such as profiling, perception, memory, planning, and action, using an established taxonomy. The tutorial also extends the discussion to multi-agent frameworks, offering insights into collaborative intelligence. Additionally, it compares popular open-source frameworks for LLM-based agent development and discusses evaluation methodologies, focusing on efficiency and safety. The tutorial aims to catalyze dialogue and partnership among practitioners, propelling forward the integration of robust and effective LLM agent systems into the production environment.
References
[1]
[n. d.]. CNBC Interview, Growth of AI in Economic Growth. https://www.youtube.com/watch?v=9Ks3DBdh9IMt=67s. Streamed: Feb 7, 2024; Accessed: June 13, 2024.
[2]
[n. d.]. HELLO gpt-4o. https://openai.com/index/hello-gpt-4o/.
[3]
Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems 35 (2022), 23716--23736.
[4]
Michal Shlapentokh-Rothman Haohan Wang Yu-Xiong Wang Andy Zhou, Kai Yan. 2024. Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models. https://arxiv.org/pdf/2310.04406. arXiv arXiv:2310.04406 (2024).
[5]
Inc crewAI. 2023. crewAI. https://github.com/crewAIInc/crewAI. Accessed: 2024-08-06.
[6]
Newman Cheng-Joshua Bradley Alex Chao-Apurva Mody Steven Truitt Jonathan Larson Darren Edge, Ha Trinh. 2024. From Local to Global: A Graph RAG Approach to Query-Focused Summarization. https://arxiv.org/pdf/2404.16130. arXiv arXiv:2404.16130 (2024).
[7]
Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al. 2023. Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023).
[8]
Difei Gao, Lei Ji, Luowei Zhou, Kevin Qinghong Lin, Joya Chen, Zihan Fan, and Mike Zheng Shou. 2023. Assistgpt: A general multi-modal assistant that can plan, execute, inspect, and learn. arXiv preprint arXiv:2306.08640 (2023).
[9]
Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680 (2024).
[10]
Shibo Hao, Yi Gu, Haodi Ma, Joshua Jiahua Hong, Zhen Wang, Daisy Zhe Wang, and Zhiting Hu. 2023. Reasoning with language model is planning with world model. arXiv preprint arXiv:2305.14992 (2023).
[11]
Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2023. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. arXiv:2308.00352 [cs.AI]
[12]
Chenxu Hu, Jie Fu, Chenzhuang Du, Simian Luo, Junbo Zhao, and Hang Zhao. 2023. Chatdb: Augmenting llms with databases as their symbolic memory. arXiv preprint arXiv:2306.03901 (2023).
[13]
Rongjie Huang, Mingze Li, Dongchao Yang, Jiatong Shi, Xuankai Chang, Zhenhui Ye, Yuning Wu, Zhiqing Hong, Jiawei Huang, Jinglin Liu, et al. 2024. Audiogpt: Understanding and generating speech, music, sound, and talking head. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 23802--23804.
[14]
Ziheng Huang, Sebastian Gutierrez, Hemanth Kamana, and Stephen MacNeil. 2023. Memory sandbox: Transparent and interactive memory management for conversational agents. In Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1--3.
[15]
Jiaju Lin, Haoran Zhao, Aochi Zhang, Yiting Wu, Huqiuyue Ping, and Qin Chen. 2023. Agentsims: An open-source sandbox for large language model evaluation. arXiv preprint arXiv:2308.04026 (2023).
[16]
Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. 2023. Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688 (2023).
[17]
Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023. Gpteval: Nlg evaluation using gpt-4 with better human alignment. arXiv preprint arXiv:2303.16634 (2023).
[18]
Microsoft. 2024. AutoGen Documentation: Introduction. https://microsoft.github.io/autogen/docs/tutorial/introduction/. Accessed: 2024-08-06.
[19]
Microsoft. 2024. Semantic Kernel. https://aka.ms/semantic-kernel. Accessed: 2024-08-06.
[20]
Xiaoyu Tian-Wei Zou Kaijiang Chen-Ming Cui Na Liu, Liangyu Chen. 2024. From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models. arXiv arXiv:2401.02777 (2024).
[21]
Yohei Nakajima. 2024. BabyAGI. https://github.com/yoheinakajima/babyagi. Accessed: 2024-08-06.
[22]
OpenAI. 2024. OpenAI Platform Documentation: Assistants Overview. https://platform.openai.com/docs/assistants/overview. Accessed: 2024-08-06.
[23]
R OpenAI. 2023. Gpt-4 technical report. arxiv 2303.08774. View in Article 2, 5 (2023).
[24]
OpenBMB. 2024. AgentVerse. https://github.com/OpenBMB/AgentVerse/. Accessed: 2024-08-06.
[25]
Joon Sung Park, Joseph O'Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 1--22.
[26]
Shishir G Patil, Tianjun Zhang, Xin Wang, and Joseph E Gonzalez. 2023. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334 (2023).
[27]
Bo Qiao, Liqun Li, Xu Zhang, Shilin He, Yu Kang, Chaoyun Zhang, Fangkai Yang, Hang Dong, Jue Zhang, Lu Wang, Minghua Ma, Pu Zhao, Si Qin, Xiaoting Qin, Chao Du, Yong Xu, Qingwei Lin, Saravan Rajmohan, and Dongmei Zhang. 2023. TaskWeaver: A Code-First Agent Framework. https://arxiv.org/abs/2311.17541. arXiv preprint arXiv:2311.17541 (2023).
[28]
Krishan Rana, Jesse Haviland, Sourav Garg, Jad Abou-Chakra, Ian Reid, and Niko Suenderhauf. 2023. Sayplan: Grounding large language models using 3d scene graphs for scalable task planning. arXiv preprint arXiv:2307.06135 (2023).
[29]
Yuhang Yao-Weizhao Jin Zhaozhuo Xu-Chaoyang He Shanshan Han, Qifan Zhang. 2024. LLM Multi-Agent Systems: Challenges and Open Problems. arXiv arXiv:2402.03578 (2024).
[30]
Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2024. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems 36 (2024).
[31]
Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2024. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems 36 (2024).
[32]
Dídac Surís, Sachit Menon, and Carl Vondrick. 2023. Vipergpt: Visual inference via python execution for reasoning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 11888--11898.
[33]
Yu Tian, Xiao Yang, Jingyuan Zhang, Yinpeng Dong, and Hang Su. 2023. Evil geniuses: Delving into the safety of llm-based agents. arXiv preprint arXiv:2311.11855 (2023).
[34]
Abdelrahman Younes-Tamim Asfour Timo Birr, Christoph Pohl. 2024. Auto-GPTP: Affordance-based Task Planning with Large Language Models. arXiv arXiv:2402.10778 (2024).
[35]
Mason Sawtell-Alex Chao Tula Masterman, Sandi Besen. 2024. The Landscape of Emerging AI Agent Architectures For Reasoning, Planning, and Tool Calling: A Survey. arXiv:2404.11584 (2024).
[36]
Hitesh Wadhwa, Rahul Seetharaman, Somyaa Aggarwal, Reshmi Ghosh, Samyadeep Basu, Soundararajan Srinivasan, Wenlong Zhao, Shreyas Chaudhari, and Ehsan Aghazadeh. 2024. From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries. arXiv preprint arXiv:2406.12824 (2024).
[37]
Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023).
[38]
Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. 2024. A survey on large language model based autonomous agents. Frontiers of Computer Science 18, 6 (2024), 1--26.
[39]
Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022).
[40]
Zihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu, Xiaojian Ma, and Yitao Liang. 2023. Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. arXiv preprint arXiv:2302.01560 (2023).
[41]
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022), 24824--24837.
[42]
Chenfei Wu, Shengming Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang, and Nan Duan. 2023. Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023).
[43]
Junlin Xie, Zhihong Chen, Ruifei Zhang, Xiang Wan, and Guanbin Li. 2024. Large Multimodal Agents: A Survey. arXiv preprint arXiv:2402.15116 (2024).
[44]
Xiaolong Chen-Xingmei Wang Hao Wang-Defu Lian Yasheng Wang Ruiming Tang Enhong Chen Xu Huang, Weiwen Liu. 2024. Understanding the planning of LLM agents: A survey. arXiv arXiv:2402.02716 (2024).
[45]
Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems 36 (2024).
[46]
Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. https://arxiv.org/abs/2210.03629. arXiv arXiv:2210.03629 (2023).
[47]
Yangbin Yu, Qin Zhang, Junyou Li, Qiang Fu, and Deheng Ye. 2024. Affordable Generative Agents. arXiv preprint arXiv:2402.02053 (2024).
[48]
Tongxin Yuan, Zhiwei He, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, et al. 2024. R-Judge: Benchmarking Safety Risk Awareness for LLM Agents. arXiv preprint arXiv:2401.10019 (2024).
[49]
Frank Xu Zhiruo Wang, Graham Neubig. 2024. Overview and Introcution to LLM Tool Use and Agents. https://cmu-agent-workshop.github.io/cmu-agent-workshop-2024-tutorial.pdf.
[50]
Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. 2024. Memo-rybank: Enhancing large language models with long-term memory. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 19724--19731.
[51]
Peng Li-Yang Liu Diyi Yang Zijun Liu, Yanzhe Zhang. 2023. Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization. arXiv arXiv:2310.02170 (2023).
Index Terms
- Frontiers of Large Language Model-Based Agentic Systems - Construction, Efficacy and Safety
Recommendations
A survey on large language model based autonomous agents
AbstractAutonomous agents have long been a research focus in academic and industry communities. Previous research often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning ...
Safety and Security in Multiagent Systems: Report on the 2nd SASEMAS workshop (SASEMAS'05)
As intelligent autonomous agents and multiagent systems' applications become more pervasive, it becomes increasingly more important to understand the risks associated with using these systems. Incorrect or inappropriate agent behaviour can have harmful ...
A Plan Based Coalition Formation Model for Multi-agent Systems
WI-IAT '11: Proceedings of the 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Volume 02This article addresses the coalition formation problem in a multi-agent context where agents plan their activities dynamically and use these plans to coordinate their actions and form suitable coalitions. In most coalition formation methods, when ...
Comments
Information & Contributors
Information
Published In
October 2024
5705 pages
Copyright © 2024 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 October 2024
Check for updates
Author Tags
Qualifiers
- Tutorial
Conference
CIKM '24
Sponsor:
CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management
October 21 - 25, 2024
ID, Boise, USA
Acceptance Rates
Overall Acceptance Rate 1,861 of 8,427 submissions, 22%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 558Total Downloads
- Downloads (Last 12 months)558
- Downloads (Last 6 weeks)275
Reflects downloads up to 18 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in