CoChat
Sign Up
Cited by 137Topic ModelingNatural Language Processing TechniquesSoftware Engineering Research

Language Models can Solve Computer Tasks

Open access
Kim, Geunwoo, Baldi, Pierre, McAleer, Stephen·2023·Advances in Neural Information Processing Systems 36
DOI 10.52202/075280-1723
Open this paper in CoChat — free accountOpen PDF

Abstract

Agents capable of carrying out general tasks on a computer can improve efficiency and productivity by automating repetitive tasks and assisting in complex problem-solving. Ideally, such agents should be able to solve new computer tasks presented to them through natural language commands. However, previous approaches to this problem require large amounts of expert demonstrations and task-specific reward functions, both of which are impractical for new tasks. In this work, we show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme where the agent Recursively Criticizes and Improves its output (RCI). The RCI approach significantly outperforms existing LLM methods for automating computer tasks and surpasses supervised learning (SL) and reinforcement learning (RL) approaches on the MiniWoB++ benchmark. We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++, using only a handful of demonstrations per task rather than tens of thousands, and without a task-specific reward function. Furthermore, we demonstrate RCI prompting's effectiveness in enhancing LLMs' reasoning abilities on a suite of natural language reasoning tasks, outperforming chain of thought (CoT) prompting with external feedback. We find that RCI combined with CoT performs better than either separately. Our code can be found here: https://github.com/posgnu/rci-agent.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.52202/075280-1723

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Self-reflection (automated recursive criticizing and subsequent self-improvement of LLM outputs by the LLM itself) can improve reasoning abilities.

    “Moreover, self-reflection, meaning the automated, recursive criticizing and subsequent self-improvement of LLM outputs by the LLM itself, is a further technique that can improve reasoning abilities (Nair et al., 2023;Kim et al., 2023).”

    From Machine Psychology (2023) · cites this paper as Kim et al., 2023

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Research works printed but not linked: 81

  1. [1][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. - · arXiv
  2. [2][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. -
  3. [3][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. - · arXiv
  4. [4][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. -
  5. [5][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. -
  6. [6][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. - · arXiv
  7. [7][7] Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, and PierreYves Oudeyer. Grounding large language models in interactive environments with online reinforcement learning. arXiv preprint arXiv:2302.02662 , 2023. - · arXiv
  8. [8][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. - · arXiv
  9. [9][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. - · arXiv
  10. [10][10] Antonia Creswell and Murray Shanahan. Faithful reasoning using large language models. arXiv preprint arXiv:2208.14271 , 2022. - · arXiv
  11. [11][11] Antonia Creswell, Murray Shanahan, and Irina Higgins. Selection-inference: Exploiting large language models for interpretable logical reasoning. arXiv preprint arXiv:2205.09712 , 2022. - · arXiv
  12. [12][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. - · arXiv
  13. [13][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. -
  14. [14][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. - · arXiv
  15. [15][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 Representations , 2020. -
  16. [16][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. - · arXiv
  17. [17][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. -
  18. [18][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 Benchmarks Track , 2022. -
  19. [19][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. -
  20. [20][20] Deep Ganguli, Amanda Askell, Nicholas Schiefer, Thomas Liao, Kamil˙ e Lukoši¯ ut˙ e, 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. - · arXiv
  21. [21][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. -
  22. [22][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. - · arXiv
  23. [23][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. -
  24. [24][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. - · arXiv
  25. [25][25] Izzeddin Gur, Ulrich Rueckert, Aleksandra Faust, and Dilek Hakkani-Tur. Learning to navigate the web. In International Conference on Learning Representations , 2019. -
  26. [26][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 , 35:30016-30030, 2022. -
  27. [27][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. -
  28. [28][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. -
  29. [29][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. -
  30. [30][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, 2022. -
  31. [31][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
  32. [32][32] Sheng Jia, Jamie Ryan Kiros, and Jimmy Ba. DOM-Q-NET: Grounded RL on structured language. In International Conference on Learning Representations , 2019. -
  33. [33][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. -
  34. [34][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. -
  35. [35][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. -
  36. [36][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. -
  37. [37][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. -
  38. [38][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. - · arXiv
  39. [39][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. - · arXiv
  40. [40][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. - · arXiv
  41. [41][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. - · arXiv
  42. [42][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. - · arXiv
  43. [43][43] Rodrigo Nogueira and Kyunghyun Cho. End-to-end goal-driven web navigation. Advances in Neural Information Processing Systems , 29, 2016. -
  44. [44][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
  45. [45][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. -
  46. [47][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. -
  47. [48][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. - · arXiv
  48. [49][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. -
  49. [50][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. -
  50. [51][51] Arkil Patel, Satwik Bhattamishra, and Navin Goyal. Are nlp models really able to solve simple math word problems? Proceedings of NAACL , 2021. -
  51. [52][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. - · arXiv
  52. [53][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. - · arXiv
  53. [54][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. -
  54. [55][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. -
  55. [56][56] Subhro Roy and Dan Roth. Solving general arithmetic word problems. EMNLP , 2016. -
  56. [57][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. -
  57. [58][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. - · arXiv
  58. [59][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. - · arXiv
  59. [60][60] Dale Schuurmans. Memory augmented large language models are computationally universal. arXiv preprint arXiv:2301.04589 , 2023. - · arXiv
  60. [61][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. -
  61. [62][62] Noah Shinn, Beck Labash, and Ashwin Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366 , 2023. - · arXiv
  62. [63][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. -
  63. [64][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:2201.11990 , 2022. - · arXiv
  64. [65][65] Shashank Srivastava, Oleksandr Polozov, Nebojsa Jojic, and Christopher Meek. Learning webbased 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. -
  65. [66][66] Zhiqing Sun, Xuezhi Wang, Yi Tay, Yiming Yang, and Denny Zhou. Recitation-augmented language models. In International Conference on Learning Representations , 2023. -
  66. [67][67] Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. Commonsenseqa: A question answering challenge targeting commonsense knowledge. Proceedings of NAACL-HLT , 2019. -
  67. [68][68] Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, HengTze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. LaMDA: Language models for dialog applications. arXiv preprint arXiv:2201.08239 , 2022. - · arXiv
  68. [69][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. - · arXiv
  69. [70][70] Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, and Denny Zhou. Selfconsistency improves chain of thought reasoning in language models. In International Conference on Learning Representations , 2023. -
  70. [71][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. - · arXiv
  71. [72][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. -
  72. [73][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. -
  73. [74][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. - · arXiv
  74. [75][75] Mengjiao Sherry Yang, Dale Schuurmans, Pieter Abbeel, and Ofir Nachum. Chain of thought imitation with procedure cloning. Advances in Neural Information Processing Systems , 35:3636636381, 2022. -
  75. [76][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. - · arXiv
  76. [77][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. -
  77. [78][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. -
  78. [79][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. -
  79. [80][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. -
  80. [81][81] Tianjun Zhang, Xuezhi Wang, Denny Zhou, Dale Schuurmans, and Joseph E. Gonzalez. TEMPERA: Test-time prompt editing via reinforcement learning. In The Eleventh International Conference on Learning Representations , 2023. -
  81. [82][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 , 2023.

Cited by

Sorted by citations

Authors
Kim, G., Baldi, P., & McAleer, S.
ORCID
McAleer, Stephen
Venue
Advances in Neural Information Processing Systems 36
Publisher
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
Published
2023
Pages
39648-39677
ISSN
1049-5258 (ISSN-L)
DOI
10.52202/075280-1723
OpenAlex
W7133210150
Cited by
137
References
0
Citations by year
2026: 15 · 2025: 41 · 2024: 65 · 2023: 16
FWCI
21.68
Type
conference paper
Language
en
Open access
Locations
  • neural information processing systems (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Science Foundation (2127309)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Research
Keywords
language models, large language models, computer tasks, task solving

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review