Elamur Research
☰
home / papers / 2023 / Language Models can Solve Computer Tasks

Language Models can Solve Computer Tasks

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "arXiv — non-exclusive license to distribute" does not allow redistributing the text itself. Original — arxiv.org/pdf/2303.17491

Summary

Agents that operate a computer from natural-language commands have usually been trained from scratch with supervised or reinforcement learning. That approach needs large sets of expert demonstrations and a hand-designed reward for every task. The authors instead use a pre-trained large language model with a prompting loop called RCI (Recursively Criticizes and Improves). The model writes a draft, is asked to find problems in it, and then revises it. For computer control, each action is chosen in three stages. Task grounding writes a high-level plan and refines it with an explicit critique. State grounding matches each plan step to HTML elements on the current page. Agent grounding puts the action in a format the executor accepts. The last two stages are refined implicitly. On MiniWoB++, RCI with InstructGPT-3+RLHF beats earlier LLM, SL and RL agents. It needs only a few demonstrations per task and no task-specific reward. The same loop also improves reasoning on benchmarks such as GSM8K. This shows that general-purpose LLMs can work as practical computer agents without expensive task-specific data.

Key points

  • RCI prompting: RCI adds two prompts after the first answer: a critique and a revision. In the explicit variant, the model writes out its critique before revising. In the implicit variant, it revises the output directly without writing a critique. The loop stops on environment feedback, after a set number of iterations, or by a heuristic.
  • Computer tasks: The tasks are split into task, state and agent grounding. The authors found that critiquing the state-grounding step once is enough. The agent mostly acts by clicking and typing.
  • MiniWoB++ results: RCI is state of the art with gpt-3.5-turbo (InstructGPT-3+RLHF). It uses a handful of demonstrations per task, while SL+RL baselines use tens of thousands. In an ablation, plain GPT-3 and InstructGPT-3 did clearly worse, which shows the value of instruction fine-tuning.
  • Reasoning tasks: With external feedback, RCI beats zero-shot prompting and slightly beats chain-of-thought (CoT). Combining RCI with CoT gives the best results.
  • Limitations and code: Long HTML pages run into context-length limits. The agent's set of actions is narrow and it plans only short-term. RCI also costs more than sampling the model once. The paper appeared at NeurIPS 2023, and the code is at github.com/posgnu/rci-agent.

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

Fields: Other

Cited by

159 papers of our library cite it (of the 140673 whose bibliographies we read); 21 of them have a page here, 138 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2303.17491 · arXiv 2303.17491

@misc{kim2023language,
  title = {{Language Models can Solve Computer Tasks}},
  author = {Kim, Geunwoo and Baldi, Pierre and McAleer, Stephen},
  year = {2023},
  doi = {10.48550/arxiv.2303.17491},
  eprint = {2303.17491},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2303.17491}
}

References

82 references, 34 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, et al. Do as I can, not as I say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691, 2022. find our card
  2. Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, 35:23716–23736, 2022. find our card
  3. 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. find our card
  4. Bowen Baker, Ilge Akkaya, Peter Zhokov, Joost Huizinga, Jie Tang, Adrien Ecoffet, Brandon Houghton, Raul Sampedro, and Jeff Clune. Video pretraining (vpt): Learning to act by watching unlabeled online videos. Advances in Neural Information Processing Systems, 35:24639–24654, 2022. find
  5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in Neural Information Processing Systems, 33:1877–1901, 2020. find
  6. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712, 2023. find our card
  7. Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, and Pierre-Yves Oudeyer. Grounding large language models in interactive environments with online reinforcement learning. arXiv preprint arXiv:2302.02662, 2023. — [arXiv:2302.02662](https://arxiv.org/abs/2302.02662) find
  8. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311, 2022. find
  9. 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. find our card
  10. Antonia Creswell and Murray Shanahan. Faithful reasoning using large language models. arXiv preprint arXiv:2208.14271, 2022. find
  11. Antonia Creswell, Murray Shanahan, and Irina Higgins. Selection-inference: Exploiting large language models for interpretable logical reasoning. arXiv preprint arXiv:2205.09712, 2022. find
  12. Damai Dai, Yutao Sun, Li Dong, Yaru Hao, Zhifang Sui, and Furu Wei. Why can GPT learn in-context? Language models secretly perform gradient descent as meta optimizers. arXiv preprint arXiv:2212.10559, 2022. find
  13. Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino, Arun Ahuja, Sheila Babayan, Felix Hill, and Rob Fergus. Collaborating with language models for embodied reasoning. In Second Workshop on Language and Reinforcement Learning, 2022. find
  14. David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A Saurous, Jascha Sohl-Dickstein, et al. Language model cascades. arXiv preprint arXiv:2207.10342, 2022. find
  15. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Repres… find
  16. Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al. PaLM-E: An embodied multimodal language model. arXiv preprint arXiv:2303.03378, 2023. find
  17. Nan Du, Yanping Huang, Andrew M Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, et al. GLaM: Efficient scaling of language models with mixture-of-experts. In International Conference on Machine Learning, pages 5547–5569. PMLR, 2022. find our card
  18. Linxi Fan, Guanzhi Wang, Yunfan Jiang, Ajay Mandlekar, Yuncong Yang, Haoyi Zhu, Andrew Tang, De-An Huang, Yuke Zhu, and Anima Anandkumar. Minedojo: Building open-ended embodied agents with internet-scale knowledge. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benc… find
  19. Hiroki Furuta, Ofir Nachum, Kuang-Huei Lee, Yutaka Matsuo, Shixiang Shane Gu, and Izzeddin Gur. Instruction-finetuned foundation models for multimodal web navigation. In Workshop on Reincarnating Reinforcement Learning at ICLR, 2023. find
  20. Deep Ganguli, Amanda Askell, Nicholas Schiefer, Thomas Liao, Kamilė Lukošiūtė, Anna Chen, Anna Goldie, Azalia Mirhoseini, Catherine Olsson, Danny Hernandez, et al. The capacity for moral self-correction in large language models. arXiv preprint arXiv:2302.07459, 2023. find our card
  21. Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, and Jonathan Berant. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346–361, 2021. find
  22. Amelia Glaese, Nat McAleese, Maja Tr˛ebacz, John Aslanides, Vlad Firoiu, Timo Ewalds, Maribeth Rauh, Laura Weidinger, Martin Chadwick, Phoebe Thacker, et al. Improving alignment of dialogue agents via targeted human judgements. arXiv preprint arXiv:2209.14375, 2022. find our card
  23. Izzeddin Gur, Natasha Jaques, Yingjie Miao, Jongwook Choi, Manoj Tiwari, Honglak Lee, and Aleksandra Faust. Environment generation for zero-shot compositional reinforcement learning. Advances in Neural Information Processing Systems, 34:4157–4169, 2021. find
  24. Izzeddin Gur, Ofir Nachum, Yingjie Miao, Mustafa Safdari, Austin Huang, Aakanksha Chowdhery, Sharan Narang, Noah Fiedel, and Aleksandra Faust. Understanding HTML with large language models. arXiv preprint arXiv:2210.03945, 2022. find
  25. Izzeddin Gur, Ulrich Rueckert, Aleksandra Faust, and Dilek Hakkani-Tur. Learning to navigate the web. In International Conference on Learning Representations, 2019. find
  26. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. An empirical analysis of compute-optimal large language model training. Advances in Neural Information Processing Systems,… find
  27. Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. Learning to solve arithmetic word problems with verb categorization. In EMNLP, pages 523–533, 2014. find our card
  28. Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International Conference on Machine Learning, pages 9118–9147. PMLR, 2022. find our card
  29. Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, et al. Inner monologue: Embodied reasoning through planning with language models. In 6th Annual Conference on Robot Learning, 2022. find
  30. Peter C Humphreys, David Raposo, Tobias Pohlen, Gregory Thornton, Rachita Chhaparia, Alistair Muldal, Josh Abramson, Petko Georgiev, Adam Santoro, and Timothy Lillicrap. A data-driven approach for learning to control computers. In International Conference on Machine Learning, pages 9466–9482. PMLR,… find
  31. Taichi Iki and Akiko Aizawa. Do BERTs learn to use browser user interface? Exploring multi-step tasks with unified vision-and-language berts. arXiv preprint arXiv:2203.07828, 2022. — [arXiv:2203.07828](https://arxiv.org/abs/2203.07828) find
  32. Sheng Jia, Jamie Ryan Kiros, and Jimmy Ba. DOM-Q-NET: Grounded RL on structured language. In International Conference on Learning Representations, 2019. find
  33. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems, 2022. find our card
  34. Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, and Siena Dumas Ang. Parsing algebraic word problems into equations. Transactions of the Association for Computational Linguistics, 3:585–597, 2015. find
  35. Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. Program induction by rationale generation: Learning to solve and explain algebraic word problems. Proceedings of ACL, 2017. find
  36. Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, and Percy Liang. Reinforcement learning on web interfaces using workflow-guided exploration. In International Conference on Learning Representations, 2018. find
  37. Ruibo Liu, Jason Wei, Shixiang Shane Gu, Te-Yen Wu, Soroush Vosoughi, Claire Cui, Denny Zhou, and Andrew M Dai. Mind’s eye: Grounded language model reasoning through simulation. In International Conference on Learning Representations, 2023. find
  38. 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. arXiv preprint arXiv:2303.17651, 2023. find
  39. Aman Madaan and Amir Yazdanbakhsh. Text and patterns: For effective chain of thought, it takes two to tango. arXiv preprint arXiv:2209.07686, 2022. find
  40. Jacob Menick, Maja Trebacz, Vladimir Mikulik, John Aslanides, Francis Song, Martin Chadwick, Mia Glaese, Susannah Young, Lucy Campbell-Gillingham, Geoffrey Irving, et al. Teaching language models to support answers with verified quotes. arXiv preprint arXiv:2203.11147, 2022. find our card
  41. Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, et al. Augmented language models: a survey. arXiv preprint arXiv:2302.07842, 2023. find our card
  42. 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. find our card
  43. Rodrigo Nogueira and Kyunghyun Cho. End-to-end goal-driven web navigation. Advances in Neural Information Processing Systems, 29, 2016. find
  44. Kolby Nottingham, Prithviraj Ammanabrolu, Alane Suhr, Yejin Choi, Hannaneh Hajishirzi, Sameer Singh, and Roy Fox. Do embodied agents dream of pixelated sheep?: Embodied decision making using language guided world modelling. arXiv preprint arXiv:2301.12050, 2023. — [arXiv:2301.12050](https://arxiv.org/abs/2301.12050) find
  45. Maxwell Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, et al. Show your work: Scratchpads for intermediate computation with language models. In Deep Learning for Code Workshop at ICLR, 2022. find our card
  46. OpenAI. Gpt-4 technical report, 2023. find our card
  47. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744, 2022. find
  48. Bhargavi Paranjape, Scott Lundberg, Sameer Singh, Hannaneh Hajishirzi, Luke Zettlemoyer, and Marco Tulio Ribeiro. ART: Automatic multi-step reasoning and tool-use for large language models. arXiv preprint arXiv:2303.09014, 2023. find
  49. Panupong Pasupat, Tian-Shun Jiang, Evan Liu, Kelvin Guu, and Percy Liang. Mapping natural language commands to web elements. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4970–4976, 2018. find
  50. Panupong Pasupat and Percy Liang. Zero-shot entity extraction from web pages. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 391–401, 2014. find
  51. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. Are nlp models really able to solve simple math word problems? Proceedings of NAACL, 2021. find our card
  52. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A Smith, and Mike Lewis. Measuring and narrowing the compositionality gap in language models. arXiv preprint arXiv:2210.03350, 2022. find
  53. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A Smith, and Mike Lewis. Measuring and narrowing the compositionality gap in language models. arXiv preprint arXiv:2210.03350, 2022. find
  54. Shreyas Sundara Raman, Vanya Cohen, Eric Rosen, Ifrah Idrees, David Paulius, and Stefanie Tellex. Planning with large language models via corrective re-prompting. Foundation Models for Decision Making workshop at NeurIPS, 2022. find
  55. Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gómez Colmenarejo, Alexander Novikov, Gabriel Barth-maron, Mai Giménez, Yury Sulsky, Jackie Kay, Jost Tobias Springenberg, et al. A generalist agent. Transactions on Machine Learning Research, 2022. find
  56. Subhro Roy and Dan Roth. Solving general arithmetic word problems. EMNLP, 2016. find our card
  57. Victor Sanh, Albert Webson, Colin Raffel, Stephen Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, et al. Multitask prompted training enables zero-shot task generalization. In International Conference on Learning Representations, 2022. find our card
  58. William Saunders, Catherine Yeh, Jeff Wu, Steven Bills, Long Ouyang, Jonathan Ward, and Jan Leike. Self-critiquing models for assisting human evaluators. arXiv preprint arXiv:2206.05802, 2022. find our card
  59. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761, 2023. find our card
  60. Dale Schuurmans. Memory augmented large language models are computationally universal. arXiv preprint arXiv:2301.04589, 2023. find
  61. Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, and Percy Liang. World of bits: An open-domain platform for web-based agents. In International Conference on Machine Learning, pages 3135–3144. PMLR, 2017. find
  62. Noah Shinn, Beck Labash, and Ashwin Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366, 2023. find our card
  63. Mohit Shridhar, Lucas Manuelli, and Dieter Fox. CLIPort: What and where pathways for robotic manipulation. In Conference on Robot Learning, pages 894–906. PMLR, 2022. find
  64. Shaden Smith, Mostofa Patwary, Brandon Norick, Patrick LeGresley, Samyam Rajbhandari, Jared Casper, Zhun Liu, Shrimai Prabhumoye, George Zerveas, Vijay Korthikanti, et al. Using deepspeed and megatron to train megatron-turing NLG 530b, a large-scale generative language model. arXiv preprint arXiv:22… find our card
  65. Shashank Srivastava, Oleksandr Polozov, Nebojsa Jojic, and Christopher Meek. Learning web-based procedures by reasoning over explanations and demonstrations in context. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7652–7662, 2020. find
  66. Zhiqing Sun, Xuezhi Wang, Yi Tay, Yiming Yang, and Denny Zhou. Recitation-augmented language models. In International Conference on Learning Representations, 2023. find
  67. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. Commonsenseqa: A question answering challenge targeting commonsense knowledge. Proceedings of NAACL-HLT, 2019. find
  68. Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. LaMDA: Language models for dialog applications. arXiv preprint arXiv:2201.08239, 2022. find our card
  69. Johannes von Oswald, Eyvind Niklasson, Ettore Randazzo, João Sacramento, Alexander Mordvintsev, Andrey Zhmoginov, and Max Vladymyrov. Transformers learn in-context by gradient descent. arXiv preprint arXiv:2212.07677, 2022. find our card
  70. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. In International Conference on Learning Representations, 2023. find our card
  71. Zihao Wang, Shaofei Cai, Anji Liu, Xiaojian Ma, and Yitao Liang. Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. arXiv preprint arXiv:2302.01560, 2023. find our card
  72. Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. Finetuned language models are zero-shot learners. In International Conference on Learning Representations, 2022. find
  73. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed H Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, 2022. find our card
  74. Sean Welleck, Ximing Lu, Peter West, Faeze Brahman, Tianxiao Shen, Daniel Khashabi, and Yejin Choi. Generating sequences by learning to self-correct. arXiv preprint arXiv:2211.00053, 2022. find our card
  75. Mengjiao Sherry Yang, Dale Schuurmans, Pieter Abbeel, and Ofir Nachum. Chain of thought imitation with procedure cloning. Advances in Neural Information Processing Systems, 35:36366– 36381, 2022. find
  76. Sherry Yang, Ofir Nachum, Yilun Du, Jason Wei, Pieter Abbeel, and Dale Schuurmans. Foundation models for decision making: Problems, methods, and opportunities. arXiv preprint arXiv:2303.04129, 2023. find
  77. Shunyu Yao, Howard Chen, John Yang, and Karthik R Narasimhan. Webshop: Towards scalable real-world web interaction with grounded language agents. In Advances in Neural Information Processing Systems, 2022. find our card
  78. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations, 2023. find our card
  79. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. STaR: Bootstrapping reasoning with reasoning. Advances in Neural Information Processing Systems, 35:15476–15488, 2022. find our card
  80. Andy Zeng, Adrian Wong, Stefan Welker, Krzysztof Choromanski, Federico Tombari, Aveek Purohit, Michael Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, et al. Socratic models: Composing zero-shot multimodal reasoning with language. In International Conference on Learning Representations, 2023. find our card
  81. Tianjun Zhang, Xuezhi Wang, Denny Zhou, Dale Schuurmans, and Joseph E. Gonzalez. TEM-PERA: Test-time prompt editing via reinforcement learning. In The Eleventh International Conference on Learning Representations, 2023. find
  82. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V Le, and Ed H. Chi. Least-to-most prompting enables complex reasoning in large language models. In The Eleventh International Conference on Learning Representations, 202… find our card