Elamur Research⌕
☰
home / papers / 2024 / Automated Design of Agentic Systems

Automated Design of Agentic Systems

Paper · 2024 · Shengran Hu, Cong Lu and Jeff Clune

Summary

Agentic systems built around foundation models, such as chain-of-thought pipelines, self-reflection loops and tool-using workflows, are usually assembled by hand through extensive manual tuning. The authors argue that this design work can be learned, and they frame it as a research area called Automated Design of Agentic Systems (ADAS). ADAS has three parts: a search space, a search algorithm and an evaluation function. Their method, Meta Agent Search, represents every agent as Python code. Because code can express any workflow, the space of possible designs is essentially unrestricted. A "meta" foundation model writes a new agent, checks it for novelty and bugs, and scores it on validation data. The agent is then stored in a growing archive that guides later proposals. The authors tested the approach on ARC puzzles and on benchmarks for reading comprehension, math, science and multi-task reasoning. The discovered agents clearly beat strong hand-built baselines. They also kept their advantage when moved to other domains and other models. This suggests that agent design itself can be automated, and the code is released.

Key points

  • Compared with hand-designed agents, the discovered agents gained 13.6 F1 points on DROP and 14.4% accuracy on MGSM. After transfer across domains, they gained 25.9% on GSM8K and 13.2% on GSM-Hard.
  • The search starts from an archive of baseline agents such as Chain-of-Thought and Self-Refine. In each iteration the meta agent applies two self-reflection passes, and it makes up to 5 repair attempts if the new agent fails at runtime.
  • In an ablation, the search began with no initial designs and still outperformed all hand-crafted baselines. In math, starting from scratch gave even better results: 67.5% versus 53.4% accuracy.
  • One run cost about $500 in OpenAI API fees on ARC and about $300 on the other domains. Most of the cost came from evaluating agents with gpt-3.5-turbo-0125.
  • The code is available at github.com/ShengranHu/ADAS.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of British ColumbiaVancouver · Canada104 works · 37,402 citations🔬Vector InstituteToronto · Canada37 works · 5,703 citations

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 works

Cite

Cite as Shengran Hu, Cong Lu and Jeff Clune. 2024. Automated Design of Agentic Systems. arXiv:2408.08435.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2408.08435 · arXiv 2408.08435

@misc{hu2024automated,
  title = {{Automated Design of Agentic Systems}},
  author = {Shengran Hu, Cong Lu and Jeff Clune},
  year = {2024},
  doi = {10.48550/arxiv.2408.08435},
  eprint = {2408.08435},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2408.08435}
}

References

114 references, 43 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dario Amodei. Machines of loving grace, October 2024. URL https://darioamodei.com/ machines-of-loving-grace. ↗
  2. Anthropic. Introducing the next generation of claude. https://www.anthropic.com/ news/claude-3-family, March 2024a. Blog post. ↗
  3. Anthropic. Introducing claude 3.5 sonnet. https://www.anthropic.com/news/ claude-3-5-sonnet, June 2024b. Blog post. ↗
  4. Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, et al. Constitutional ai: Harmlessness from ai feedback. arXiv preprint arXiv:2212.08073, 2022.
  5. Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Trevor Darrell, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, et al. Managing extreme ai risks amid rapid progress. Science, 384(6698):842–845, 2024. find
  6. N Bostrom. Existential Risks: analyzing human extinction scenarios and related hazards. Journal of Evolution and Technology, 9, 2002. find
  7. Robert S Boyer and J Strother Moore. A mechanical proof of the Turing completeness of pure LISP. Citeseer, 1983. find
  8. Harrison Chase. What is an agent? what-is-an-agent/, June 2024. Blog post. https://blog.langchain.dev/ ↗
  9. Banghao Chen, Zhaofeng Zhang, Nicolas Langrené, and Shengxin Zhu. Unleashing the potential of prompt engineering in large language models: a comprehensive review. arXiv preprint arXiv:2310.14735, 2023a.
  10. Guangyao Chen, Siwei Dong, Yu Shu, Ge Zhang, Sesay Jaward, Karlsson Börje, Jie Fu, and Yemin Shi. Autoagents: The automatic agents generation framework. arXiv preprint, 2023b. find
  11. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374, 2021.
  12. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, et al. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors. In The Twelfth International Conference on Learning Representations, 2023c.
  13. Ching-An Cheng, Allen Nie, and Adith Swaminathan. Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and llms. Advances in Neural Information Processing Systems, 37:71596–71642, 2024. find
  14. Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E. Gonzalez, and Ion Stoica. Chatbot arena: An open platform for evaluating llms by human preference, 2024.
  15. François Chollet. On the measure of intelligence. arXiv preprint arXiv:1911.01547, 2019. find
  16. Jeff Clune. Ai-gas: Ai-generating algorithms, an alternate paradigm for producing general artificial intelligence. arXiv preprint arXiv:1905.10985, 2019. — [arXiv:1905.10985](https://arxiv.org/abs/1905.10985) find
  17. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021.
  18. Antoine Cully and Yiannis Demiris. Quality and diversity optimization: A unifying modular framework. IEEE Transactions on Evolutionary Computation, 22(2):245–259, 2017. find
  19. N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), volume 1, pp. 886–893 vol. 1, 2005. doi: 10.1109/CVPR.2005.177. — [doi:10.1109/cvpr.2005.177](https://doi.org/10.1109/cvpr.2005.177) find
  20. Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and TAMT Meyarivan. A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE transactions on evolutionary computation, 6(2): 182–197, 2002. find
  21. Aaron Dharna, Amy K Hoover, Julian Togelius, and Lisa B Soros. Transfer dynamics in emergent evolutionary curricula. IEEE Transactions on Games, 15(2):157–170, 2022. find
  22. Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. Improving factuality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325, 2023.
  23. Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs. In Jill Burstein, Christy Doran, and Thamar Solorio (eds.), Proceedings of the 2019 Conference of the North American Chap…
  24. Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, and Pieter Abbeel. RLˆ2: Fast reinforcement learning via slow reinforcement learning. In International Conference on Learning Representations, 2017. find
  25. Adrien Ecoffet, Jeff Clune, and Joel Lehman. Open questions in creating safe open-ended AI: Tensions between control and creativity. In Conference on Artificial Life, pp. 27–35. MIT Press, 2020. find
  26. Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter. Neural architecture search: A survey. Journal of Machine Learning Research, 20(55):1–21, 2019. find
  27. Maxence Faldor, Jenny Zhang, Antoine Cully, and Jeff Clune. Omni-epic: Open-endedness via models of human notions of interestingness with environments programmed in code. arXiv preprint arXiv:2405.15568, 2024. find
  28. Chrisantha Fernando, Dylan Sunil Banarse, Henryk Michalewski, Simon Osindero, and Tim Rocktäschel. Promptbreeder: Self-referential self-improvement via prompt evolution, 2024.
  29. Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning, pp. 1126–1135. PMLR, 2017.
  30. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. Pal: Program-aided language models. In International Conference on Machine Learning, pp. 10764–10799. PMLR, 2023. find
  31. Ryan Greenblatt. Getting 50% sota on arc-agi with gpt-4. https://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt, July 2024. Technical Report. ↗
  32. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding. In International Conference on Learning Representations, 2021.
  33. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023.
  34. Shengran Hu and Jeff Clune. Thought Cloning: Learning to think while acting by imitating human thinking. Advances in Neural Information Processing Systems, 36, 2024. find
  35. Shengran Hu, Ran Cheng, Cheng He, Zhichao Lu, Jing Wang, and Miao Zhang. Accelerating multi-objective neural architecture search by random-weight evaluation. Complex & Intelligent Systems, pp. 1–10, 2021. find
  36. Shihua Huang, Zhichao Lu, Kalyanmoy Deb, and Vishnu Naresh Boddeti. Revisiting residual networks for adversarial robustness. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8202–8211, 2023. find
  37. Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren. Automated machine learning: methods, systems, challenges. Springer Nature, 2019. find
  38. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. SWE-bench: Can language models resolve real-world github issues? In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=VTF8yNQM66. ↗
  39. Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Saiful Haq, Ashutosh Sharma, Thomas T Joshi, Hanna Moazam, Heather Miller, et al. Dspy: Compiling declarative language model calls into state-of-the-art pipelines. In The Twelfth International Conference on Learning Re… find
  40. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 2012.
  41. Abrahim Ladha. Lecture 11: Turing-completeness. https://faculty.cc.gatech.edu/ ˜ladha/S24/4510/L11.pdf, 2024. CS 4510 Automata and Complexity, February 21st, 2024, Scribed by Rishabh Singhal. ↗
  42. LangChainAI. Langchain: Build context-aware reasoning applications. https://github.com/langchain-ai/langchain, 2022. ↗
  43. Joel Lehman and Kenneth O Stanley. Abandoning objectives: Evolution through the search for novelty alone. Evolutionary computation, 19(2):189–223, 2011. find
  44. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33: 9459–9474, 2020…
  45. Zelong Li, Shuyuan Xu, Kai Mei, Wenyue Hua, Balaji Rama, Om Raheja, Hao Wang, He Zhu, and Yongfeng Zhang. Autoflow: Automated workflow generation for large language model agents. arXiv preprint arXiv:2407.12821, 2024. — [arXiv:2407.12821](https://arxiv.org/abs/2407.12821) find
  46. Fei Liu, Tong Xialiang, Mingxuan Yuan, Xi Lin, Fu Luo, Zhenkun Wang, Zhichao Lu, and Qingfu Zhang. Evolution of heuristics: Towards efficient automatic algorithm design using large language model. In Forty-first International Conference on Machine Learning, 2024. find
  47. Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. Dynamic llm-agent network: An llm-agent collaboration framework with agent team optimization. arXiv preprint arXiv:2310.02170, 2023.
  48. Chris Lu, Sebastian Towers, and Jakob Foerster. Arbitrary order meta-learning with simple population-based evolution. In ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference. find
  49. Chris Lu, Samuel Holt, Claudio Fanconi, Alex J Chan, Jakob Foerster, Mihaela van der Schaar, and Robert Tjarko Lange. Discovering preference optimization algorithms with and for large language models. arXiv preprint arXiv:2406.08414, 2024a. find
  50. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. The AI Scientist: Towards fully automated open-ended scientific discovery. arXiv preprint arXiv:2408.06292, 2024b.
  51. Cong Lu, Shengran Hu, and Jeff Clune. Intelligent go-explore: Standing on the shoulders of giant foundation models. arXiv preprint arXiv:2405.15143, 2024c. find
  52. Zhichao Lu, Ian Whalen, Vishnu Boddeti, Yashesh Dhebar, Kalyanmoy Deb, Erik Goodman, and Wolfgang Banzhaf. Nsga-net: neural architecture search using multi-objective genetic algorithm. In Proceedings of the genetic and evolutionary computation conference, pp. 419–427, 2019. find
  53. Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayara-man, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Eureka: Human-level reward design via coding large language models. In The Twelfth International Conference on Learning Representations, 2023.
  54. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36, 2024. find
  55. Elliot Meyerson, Mark J Nelson, Herbie Bradley, Adam Gaier, Arash Moradi, Amy K Hoover, and Joel Lehman. Language model crossover: Variation through few-shot prompting. arXiv preprint arXiv:2302.12170, 2023. — [arXiv:2302.12170](https://arxiv.org/abs/2302.12170) find
  56. Shen-yun Miao, Chao-Chun Liang, and Keh-Yih Su. A diverse corpus for evaluating and developing english math word problem solvers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 975–984, 2020. find
  57. Jean-Baptiste Mouret and Jeff Clune. Illuminating search spaces by mapping elites. arXiv preprint arXiv:1504.04909, 2015. — [arXiv:1504.04909](https://arxiv.org/abs/1504.04909) find
  58. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, et al. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332, 2021.
  59. Andrew Ng. Issue 253. https://www.deeplearning.ai/the-batch/issue-253/, June 2024. Newsletter issue. ↗
  60. Ben Norman and Jeff Clune. First-explore, then exploit: Meta-learning intelligent exploration. arXiv preprint arXiv:2307.02276, 2023. — [arXiv:2307.02276](https://arxiv.org/abs/2307.02276) find
  61. OpenAI. Introducing chatgpt. https://openai.com/index/chatgpt/, November 2022. Blog post. ↗
  62. OpenAI. Simple evals, 2023. URL https://github.com/openai/simple-evals. Accessed: 2024-08-10. ↗
  63. OpenAI. Gpt-4 technical report, 2024.
  64. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pp. 1–22, 2023. find
  65. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. Are NLP models really able to solve simple math word problems? In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2080– 2094, Online, June 2021. Asso…
  66. Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, and Maosong Sun. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023.
  67. Chen Qian, Zihao Xie, Yifei Wang, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, and Maosong Sun. Scaling large-language-model-based multi-agent collaboration. arXiv preprint arXiv:2406.07155, 2024.
  68. Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, and Ji-Rong Wen. Tool learning with large language models: A survey. arXiv preprint arXiv:2405.17935, 2024.
  69. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, 36, 2024.
  70. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. Gpqa: A graduate-level google-proof q&a benchmark, 2023.
  71. Toran Bruce Richards. Autogpt. https://github.com/Significant-Gravitas/ AutoGPT, 2023. GitHub repository. ↗
  72. Tim Rocktäschel. Artificial Intelligence: 10 Things You Should Know. Seven Dials, September 2024. ISBN 978-1399626521. find
  73. Md Omar Faruk Rokon, Risul Islam, Ahmad Darki, Evangelos E Papalexakis, and Michalis Faloutsos. SourceFinder: Finding malware Source-Code from publicly available repositories in GitHub. In 23rd International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2020), pp. 149–163, 2020. find
  74. Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M Pawan Kumar, Emilien Dupont, Francisco JR Ruiz, Jordan S Ellenberg, Pengming Wang, Omar Fawzi, et al. Mathematical discoveries from program search with large language models. Nature, 625(7995):468–475, 2024.
  75. Timo Schick, Jane Dwivedi-Yu, Roberto Dessi, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. Toolformer: Language models can teach themselves to use tools. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. URL https://ope…
  76. Jurgen Schmidhuber. Evolutionary principles in self-referential learning. on learning now to learn: The meta-meta-meta...-hook. Diploma thesis, Technische Universitat Munchen, Germany, 14 May 1987. URL http://www.idsia.ch/˜juergen/diploma.html. ↗
  77. Jürgen Schmidhuber. Gödel machines: self-referential universal problem solvers making provably optimal self-improvements. arXiv preprint cs/0309048, 2003. find
  78. Sander Schulhoff, Michael Ilie, Nishant Balepur, Konstantine Kahadze, Amanda Liu, Chenglei Si, Yinheng Li, Aayush Gupta, HyoJung Han, Sevien Schulhoff, et al. The prompt report: A systematic survey of prompting techniques. arXiv preprint arXiv:2406.06608, 2024.
  79. Xuan Shen, Yaohua Wang, Ming Lin, Yilun Huang, Hao Tang, Xiuyu Sun, and Yanzhi Wang. Deep-mad: Mathematical architecture design for deep convolutional neural network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6163–6173, 2023. find
  80. Freda Shi, Mirac Suzgun, Markus Freitag, Xuezhi Wang, Suraj Srivats, Soroush Vosoughi, Hyung Won Chung, Yi Tay, Sebastian Ruder, Denny Zhou, Dipanjan Das, and Jason Wei. Language models are multilingual chain-of-thought reasoners. In The Eleventh International Conference on Learning Representations,…
  81. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36, 2023.
  82. Kenneth O Stanley and Joel Lehman. Why greatness cannot be planned: The myth of the objective. Springer, 2015. find
  83. Kenneth O Stanley, Jeff Clune, Joel Lehman, and Risto Miikkulainen. Designing neural networks through neuroevolution. Nature Machine Intelligence, 1(1):24–35, 2019. find
  84. Richard S. Sutton. The bitter lesson, 2019. URL http://www.incompleteideas.net/ IncIdeas/BitterLesson.html. ↗
  85. Richard S Sutton and Andrew G Barto. Reinforcement learning: An introduction. MIT press, 2018. find
  86. Jon Turow. The rise of ai agent infrastructure. June 2024. URL https://www.madrona.com/ the-rise-of-ai-agent-infrastructure/. ↗
  87. Sai Vemprala, Rogerio Bonatti, Arthur Bucker, and Ashish Kapoor. Chatgpt for robotics: Design principles and model abilities. Technical Report MSR-TR-2023-8, Microsoft, February 2023. URL https://www.microsoft.com/en-us/research/publication/ chatgpt-for-robotics-design-principles-and-model-abilities… ↗
  88. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv: Arxiv-2305.16291, 2023a. find
  89. Jane X Wang, Zeb Kurth-Nelson, Dhruva Tirumala, Hubert Soyer, Joel Z Leibo, Remi Munos, Charles Blundell, Dharshan Kumaran, and Matt Botvinick. Learning to reinforcement learn. arXiv preprint arXiv:1611.05763, 2016. — [arXiv:1611.05763](https://arxiv.org/abs/1611.05763) find
  90. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6):186345, 2024.
  91. Rui Wang, Joel Lehman, Jeff Clune, and Kenneth O. Stanley. Poet: open-ended coevolution of environments and their optimized solutions. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’19, pp. 142–151, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 978… — [doi:10.1145/3321707.3321799](https://doi.org/10.1145/3321707.3321799) find
  92. Rui Wang, Joel Lehman, Aditya Rawal, Jiale Zhi, Yulun Li, Jeffrey Clune, and Kenneth Stanley. Enhanced poet: Open-ended reinforcement learning through unbounded invention of learning challenges and their solutions. In International conference on machine learning, pp. 9940–9951. PMLR, 2020. find
  93. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, 2023b.
  94. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022.
  95. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155, 2023.
  96. Benfeng Xu, An Yang, Junyang Lin, Quan Wang, Chang Zhou, Yongdong Zhang, and Zhendong Mao. Expertprompting: Instructing large language models to be distinguished experts. arXiv preprint arXiv:2305.14688, 2023.
  97. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. Large language models as optimizers. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=Bb4VGOWELI. ↗
  98. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum? id=WE_vluYUL-X. ↗
  99. Wenhao Yu, Nimrod Gileadi, Chuyuan Fu, Sean Kirmani, Kuang-Huei Lee, Montserrat Gonzalez Arenas, Hao-Tien Lewis Chiang, Tom Erez, Leonard Hasenclever, Jan Humplik, et al. Language to rewards for robotic skill synthesis. In Conference on Robot Learning, pp. 374–404. PMLR, 2023. find
  100. Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, and Deqing Yang. Evoagent: Towards automatic multi-agent generation via evolutionary algorithms. arXiv preprint arXiv:2406.14228, 2024. find
  101. Eliezer Yudkowsky et al. Artificial Intelligence as a positive and negative factor in global risk. Global catastrophic risks, 1(303):184, 2008. find
  102. Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, and James Zou. Textgrad: Automatic” differentiation” via text. arXiv preprint arXiv:2406.07496, 2024.
  103. Matei Zaharia, Omar Khattab, Lingjiao Chen, Jared Quincy Davis, Heather Miller, Chris Potts, James Zou, Michael Carbin, Jonathan Frankle, Naveen Rao, and Ali Ghodsi. The shift from models to compound ai systems. https://bair.berkeley.edu/blog/2024/02/18/ compound-ai-systems/, 2024. ↗
  104. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. STar: Bootstrapping reasoning with reasoning. In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (eds.), Advances in Neural Information Processing Systems, 2022. URL https://openreview.net/ forum?id=_3ELRdg2sgI. ↗
  105. Eric Zelikman, Eliana Lorch, Lester Mackey, and Adam Tauman Kalai. Self-taught optimizer (stop): Recursively self-improving code generation. In First Conference on Language Modeling, 2024. find
  106. Jenny Zhang, Joel Lehman, Kenneth Stanley, and Jeff Clune. OMNI: Open-endedness via models of human notions of interestingness. In The Twelfth International Conference on Learning Representations, 2024a. URL https://openreview.net/forum?id=AgM3MzT99c. ↗
  107. Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, and Qingyun Wu. Offline training of language model agents with functions as learnable weights. In Forty-first International Conference on Machine Learning, 2024b. find
  108. Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. A survey on the memory mechanism of large language model based agents. arXiv preprint arXiv:2404.13501, 2024c. find
  109. Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H Chi, Quoc V Le, and Denny Zhou. Take a step back: Evoking reasoning via abstraction in large language models. arXiv preprint arXiv:2310.06117, 2023.
  110. Pei Zhou, Jay Pujara, Xiang Ren, Xinyun Chen, Heng-Tze Cheng, Quoc V Le, Ed H Chi, Denny Zhou, Swaroop Mishra, and Huaixiu Steven Zheng. Self-discover: Large language models self-compose reasoning structures. arXiv preprint arXiv:2402.03620, 2024a. find
  111. Wangchunshu Zhou, Yixin Ou, Shengwei Ding, Long Li, Jialong Wu, Tiannan Wang, Jiamin Chen, Shuai Wang, Xiaohua Xu, Ningyu Zhang, et al. Symbolic learning enables self-evolving agents. arXiv preprint arXiv:2406.18532, 2024b.
  112. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. Gptswarm: Language agents as optimizable graphs. In Forty-first International Conference on Machine Learning, 2024.
  113. Luisa Zintgraf, Sebastian Schulze, Cong Lu, Leo Feng, Maximilian Igl, Kyriacos Shiarlis, Yarin Gal, Katja Hofmann, and Shimon Whiteson. Varibad: Variational bayes-adaptive deep rl via meta-learning. Journal of Machine Learning Research, 22(289):1–39, 2021a. find
  114. Luisa M Zintgraf, Leo Feng, Cong Lu, Maximilian Igl, Kristian Hartikainen, Katja Hofmann, and Shimon Whiteson. Exploration in approximate hyper-state space for meta reinforcement learning. In International Conference on Machine Learning, pp. 12991–13001. PMLR, 2021b. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hu-2024-automated-design-agentic-systems/