2024

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

Du, Yu, Wei, Fangyun, Zhang, Hongyang

Understand

We introduce AnyTool, a large language model agent designed to revolutionize the utilization of a vast array of tools in addressing user queries.

We utilize over 16,000 APIs from Rapid API, operating under the assumption that a subset of these APIs could potentially resolve the queries.
AnyTool primarily incorporates three elements: an API retriever with a hierarchical structure, a solver aimed at resolving user queries using a selected set of API candidates, and a self-reflection mechanism, which re-activates AnyTool if the initial solution proves impracticable.
AnyTool is powered by the function calling feature of GPT-4, eliminating the need for training external modules.

Built on

Improving language understanding by generative pre-training
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al · 2018
Earlier work this paper cites.
Language models are unsupervised multitask learners
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al · 2019
Earlier work this paper cites.
Language models are few-shot learners
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al · 2020
Earlier work this paper cites.
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al · 2022
Earlier work this paper cites.
TALM: Tool augmented language models
Original
Parisi, A., Zhao, Y., and Fiedel, N · 2022
Earlier work this paper cites.
LaMDA: Language models for dialog applications
Original
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., Du, Y., et al · 2022
Earlier work this paper cites.
Self-instruct: Aligning language model with self generated instructions
Original
Wang, Y., Kordi, Y., Mishra, S., Liu, A., Smith, N. A., Khashabi, D., and Hajishirzi, H · 2022
Earlier work this paper cites.
Chain-of-thought prompting elicits reasoning in large language models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al · 2022
Earlier work this paper cites.
GPT-4 technical report
Original
Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al · 2023
Earlier work this paper cites.

Similar

Factuality challenges in the era of large language models
Original
Augenstein, I., Baldwin, T., Cha, M., Chakraborty, T., Ciampaglia, G. L., Corney, D., DiResta, R., Ferrara, E., Hale, S., Halevy, A., et al · 2023
Cited alongside, same era.
Large language models as tool makers
Original
Cai, T., Wang, X., Ma, T., Chen, X., and Zhou, D · 2023
Cited alongside, same era.
PaLM: Scaling language modeling with pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al · 2023
Cited alongside, same era.
ToolkenGPT: Augmenting frozen language models with massive tools via tool embeddings
Original
Hao, S., Liu, T., Wang, Z., and Hu, Z · 2023
Cited alongside, same era.
Tool documentation enables zero-shot tool-usage with large language models
Original
Hsieh, C.-Y., Chen, S.-A., Li, C.-L., Fujii, Y., Ratner, A., Lee, C.-Y., Krishna, R., and Pfister, T · 2023
Cited alongside, same era.
Large language models cannot self-correct reasoning yet
Original
Huang, J., Chen, X., Mishra, S., Zheng, H. S., Yu, A. W., Song, X., and Zhou, D · 2023
Cited alongside, same era.
API-Bank: A comprehensive benchmark for tool-augmented LLMs
Li, M., Zhao, Y., Yu, B., Song, F., Li, H., Yu, H., Li, Z., Huang, F., and Li, Y · 2023
Cited alongside, same era.
Gorilla: Large language model connected with massive apis
Original
Patil, S. G., Zhang, T., Wang, X., and Gonzalez, J. E · 2023
Cited alongside, same era.
Direct preference optimization: Your language model is secretly a reward model
Original
Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C. D., and Finn, C · 2023
Cited alongside, same era.
Tool learning with foundation models
Original
Qin, Y., Hu, S., Lin, Y., Chen, W., Ding, N., Cui, G., Zeng, Z., Huang, Y., Xiao, C., Han, C., et al
Cited in the paper.
ToolLLM: Facilitating large language models to master 16000+ real-world APIs
Original
Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., et al
Cited in the paper.
Llama: Open and efficient foundation language models
Original
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al
Cited in the paper.

Then

TPTU: Task planning and tool usage of large language model-based ai agents
Original
Ruan, J., Chen, Y., Zhang, B., Xu, Z., Bao, T., Du, G., Shi, S., Mao, H., Zeng, X., and Zhao, R · 2023
Later among the works it cites.
Toolformer: Language models can teach themselves to use tools
Original
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., and Scialom, T · 2023
Later among the works it cites.
HuggingGPT: Solving ai tasks with ChatGPT and its friends in huggingface
Original
Shen, Y., Song, K., Tan, X., Li, D., Lu, W., and Zhuang, Y · 2023
Later among the works it cites.
RestGPT: Connecting large language models with real-world applications via RESTful APIs
Song, Y., Xiong, W., Zhu, D., Li, C., Wang, K., Tian, Y., and Li, S · 2023
Later among the works it cites.
ToolAlpaca: Generalized tool learning for language models with 3000 simulated cases
Original
Tang, Q., Deng, Z., Lin, H., Han, X., Liang, Q., and Sun, L · 2023
Later among the works it cites.
On the tool manipulation capability of open-source large language models
Original
Xu, Q., Hong, F., Li, B., Hu, C., Chen, Z., and Zhang, J · 2023
Later among the works it cites.
Self-play fine-tuning converts weak language models to strong language models
Original
Chen, Z., Deng, Y., Yuan, H., Ji, K., and Gu, Q · 2024
Closest in time.
RAIN: Your language models can align themselves without finetuning
Li, Y., Wei, F., Zhao, J., Zhang, C., and Zhang, H · 2024
Closest in time.
Self-rewarding language models
Original
Yuan, W., Pang, R. Y., Cho, K., Sukhbaatar, S., Xu, J., and Weston, J · 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…

Reading the bibliography…