Fetching the paper…

Reading the bibliography…

2024

Coalitions of Large Language Models Increase the Robustness of AI Agents

Mangal, Prattyush, Mak, Carol, Kanakis, Theo et al.

Original
PDF
Post on X

Understand

The emergence of Large Language Models (LLMs) have fundamentally altered the way we interact with digital systems and have led to the pursuit of LLM powered AI agents to assist in daily workflows.

LLMs, whilst powerful and capable of demonstrating some emergent properties, are not logical reasoners and often struggle to perform well at all sub-tasks carried out by an AI agent to plan and execute a workflow.
While existing studies tackle this lack of proficiency by generalised pretraining at a huge scale or by specialised fine-tuning for tool use, we assess if a system comprising of a coalition of pretrained LLMs, each exhibiting specialised performance at individual sub-tasks, can match the performance of single model agents.
The coalition of models approach showcases its potential for building robustness and reducing the operational costs of these AI agents by leveraging traits exhibited by specific models.

Coalitions of Large Language Models Increase the Robustness of AI Agents · Around

Built on

Fielding, R.T.: Architectural styles and the design of network-based software architectures. University of California, Irvine (2000)
2000
Earlier work this paper cites.
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Original
2018
Earlier work this paper cites.
Ofoeda, J., Boateng, R., Effah, J.: Application programming interface (api) research: A review of the past to inform the future. International Journal of Enterprise Information Systems (IJEIS) Vol 15 (3), 76–95 (2019)
2019
Earlier work this paper cites.
Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., Steinhardt, J.: Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)
Original
2020
Earlier work this paper cites.
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., Cao, Y.: React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)
Original
2022
Earlier work this paper cites.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q.V., Zhou, D., et al.: Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems Vol 35, 24824–24837 (2022)
2022
Earlier work this paper cites.
Fedus, W., Dean, J., Zoph, B.: A review of sparse expert models in deep learning. arXiv preprint arXiv:2209.01667 (2022)
Original
2022
Earlier work this paper cites.
Tay, Y., Dehghani, M., Tran, V.Q., Garcia, X., Wei, J., Wang, X., Chung, H.W., Shakeri, S., Bahri, D., Schuster, T., et al.: Ul2: Unifying language learning paradigms. arXiv preprint arXiv:2205.05131 (2022)
Original
2022
Earlier work this paper cites.
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al.: Training language models to follow instructions with human feedback. Advances in neural information processing systems Vol 35, 27730–27744 (2022)
2022
Earlier work this paper cites.
Sevilla, J., Heim, L., Ho, A., Besiroglu, T., Hobbhahn, M., Villalobos, P.: Compute trends across three eras of machine learning. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2022). IEEE
2022
Earlier work this paper cites.
Gugger, S., Debut, L., Wolf, T., Schmid, P., Mueller, Z., Mangrulkar, S., Sun, M., Bossan, B.: Accelerate: Training and inference at scale made simple, efficient and adaptable. https://github.com/huggingface/accelerate (2022)
2022
Earlier work this paper cites.

Similar

Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)
Original
2023
Cited alongside, same era.
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)
Original
2023
Cited alongside, same era.
Wu, Q., Bansal, G., Zhang, J., Wu, Y., Zhang, S., Zhu, E., Li, B., Jiang, L., Zhang, X., Wang, C.: Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155 (2023)
Original
2023
Cited alongside, same era.
Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)
Original
2023
Cited alongside, same era.

Then

Jiang, A.Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D.S., Casas, D.d.l., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)
Original
2023
Later among the works it cites.
Ainslie, J., Lee-Thorp, J., Jong, M., Zemlyanskiy, Y., Lebrón, F., Sanghai, S.: Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:2305.13245 (2023)
Original
2023
Later among the works it cites.
Roziere, B., Gehring, J., Gloeckle, F., Sootla, S., Gat, I., Tan, X.E., Adi, Y., Liu, J., Remez, T., Rapin, J., et al.: Codellama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)
Original
2023
Later among the works it cites.
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al.: A survey on large language model based autonomous agents. Frontiers of Computer Science Vol 18 (6), 186345 (2024)
2024
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Song, Y., Xiong, W., Zhu, D., Li, C., Wang, K., Tian, Y., Li, S.: Restgpt: Connecting large language models with real-world applications via restful apis. arXiv preprint arXiv:2306.06624 (2023)

2023

Cited alongside, same era.

Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., et al.: Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789 (2023)

2023

Cited alongside, same era.

Tang, Q., Deng, Z., Lin, H., Han, X., Liang, Q., Sun, L.: ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases (2023)

2023

Cited alongside, same era.

Patil, S.G., Zhang, T., Wang, X., Gonzalez, J.E.: Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334 (2023)

2023

Cited alongside, same era.

Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R.K.-W., Lim, E.-P.: Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:2305.04091 (2023)

2023

Cited alongside, same era.

Valmeekam, K., Marquez, M., Kambhampati, S.: Can large language models really improve by self-critiquing their own plans? arXiv preprint arXiv:2310.08118 (2023)

2023

Cited alongside, same era.

Chiang, W.-L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J.E., Stoica, I., Xing, E.P.: Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https://lmsys.org/blog/2023-03-30-vicuna/

2023

Cited alongside, same era.

Kambhampati, S., Valmeekam, K., Guan, L., Stechly, K., Verma, M., Bhambri, S., Saldyt, L., Murthy, A.: Llms can’t plan, but can help planning in llm-modulo frameworks. arXiv preprint arXiv:2402.01817 (2024)

2024

Closest in time.

LangChain-AI: OpenGPTs. GitHub (2024). https://github.com/langchain-ai/opengpts

2024

Closest in time.

Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., Scialom, T.: Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems Vol 36 (2024)

2024

Closest in time.

Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems Vol 36 (2024)

2024

Closest in time.

Jiang, A.Q., Sablayrolles, A., Roux, A., Mensch, A., Savary, B., Bamford, C., Chaplot, D.S., Casas, D.d.l., Hanna, E.B., Bressand, F., et al.: Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)

2024

Closest in time.

Multi-task Language Understanding on MMLU model performance (2024). https://paperswithcode.com/sota/multi-task-language-understanding-on-mmlu

2024

Closest in time.

Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems Vol 36 (2024)

2024

Closest in time.