Elamur Research⌕
☰
home / papers / 2023 / Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning

Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning

Paper · 2023 · Zhiting Hu and Tianmin Shu

Summary

This position paper argues that large language models (LLMs) such as GPT-4 reason and plan unreliably across language, embodied, and social tasks. The authors trace this to three weaknesses. In inference, LLMs generate text left to right in one pass. In learning, they imitate text corpora without interacting with the world. In modeling, language is ambiguous, lacks grounding, and is an inefficient medium for physical detail.

Drawing on cognitive science, the authors propose the LAW framework, which links language models, agent models, and world models. World and agent models act as the abstraction of reasoning: they hold beliefs, goals or rewards, predictions of action outcomes, and deliberate planning. LMs serve as the computational backend that implements these models or their parts.

The paper presents no new dataset or experiments. Instead, it surveys related work and sets out a research roadmap: training LMs on embodied and social experience, multimodal world modeling, and tool use. Its value is a unifying view that may guide work toward more robust, human-like machine reasoning.

Key points

  • Authors are Zhiting Hu (UCSD) and Tianmin Shu (JHU). Figure 1 shows GPT-4 failing simple language, embodied (including Blocks World), and social reasoning tasks.
  • The three models are formalized as follows:
    • An LM predicts the next token, P(x_t | x_1:t−1).
    • A world model gives state-transition probabilities, T(s′ | s, a).
    • An agent model adds goals, beliefs about the world, and beliefs about other agents. Reasoning about others' minds requires nested agent models.
  • The proposed roadmap includes:
    • fine-tuning LMs on embodied experiences while preserving their language skills;
    • social learning from humans and other models;
    • tool use via fine-tuning, in-context learning, or tool embeddings.
  • For multimodal world modeling, the authors judge models like GPT-4V, LLaVA, and Gemini insufficient because they cannot generate future states sequentially. They envision a multi-level world model that combines symbolic states (e.g., scene graphs) with action-conditioned, diffusion-based video prediction.
  • Acknowledged limitations:
    • The framework relies on discrete symbolic representations.
    • It assumes behavior is driven by goals, overlooking influences such as social norms.
    • It does not address the inherent limits of Transformer architectures.

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, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 19,503 worksArtificial Intelligence · 18,805 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1,948 worksLegal AI · 157 works

Cite

Cite as Zhiting Hu and Tianmin Shu. 2023. Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning. arXiv:2312.05230.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2312.05230 · arXiv 2312.05230

@misc{hu2023language,
  title = {{Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning}},
  author = {Zhiting Hu and Tianmin Shu},
  year = {2023},
  doi = {10.48550/arxiv.2312.05230},
  eprint = {2312.05230},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2312.05230}
}

References

118 references, 38 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. M. Ahn, A. Brohan, N. Brown, Y. Chebotar, O. Cortes, B. David, C. Finn, K. Gopalakrishnan, K. Hausman, A. Herzog, et al. Do as i can, not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691, 2022.
  2. K. R. Allen, K. A. Smith, and J. B. Tenenbaum. Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning. PNAS, 2020. find
  3. K. R. Allen, Y. Rubanova, T. Lopez-Guevara, W. Whitney, A. Sanchez-Gonzalez, P. Battaglia, and T. Pfaff. Learning rigid dynamics with face interaction graph networks. arXiv preprint arXiv:2212.03574, 2022. — [arXiv:2212.03574](https://arxiv.org/abs/2212.03574) find
  4. A. Anand, E. Racah, S. Ozair, Y. Bengio, M.-A. Côté, and R. D. Hjelm. Unsupervised state representation learning in atari. Advances in neural information processing systems, 32, 2019. find
  5. J. Andreas. Language models as agent models. arXiv preprint arXiv:2212.01681, 2022.
  6. AutoGPT. Autogpt, 2022. URL https://autogpt.net. ↗
  7. C. L. Baker, R. Saxe, and J. B. Tenenbaum. Action understanding as inverse planning. Cognition, 113(3):329–349, 2009. find
  8. C. L. Baker, J. Jara-Ettinger, R. Saxe, and J. B. Tenenbaum. Rational quantitative attribution of beliefs, desires and percepts in human mentalizing. Nature Human Behaviour, 1(4):1–10, 2017. find
  9. C.-P. Bara, S. CH-Wang, and J. Chai. Mindcraft: Theory of mind modeling for situated dialogue in collaborative tasks. In Conference on Empirical Methods in Natural Language Processing, 2021. find
  10. P. W. Battaglia, J. B. Hamrick, and J. B. Tenenbaum. Simulation as an engine of physical scene understanding. PNAS, 2013. find
  11. F. Berkenkamp, M. Turchetta, A. Schoellig, and A. Krause. Safe model-based reinforcement learning with stability guarantees. Advances in neural information processing systems, 30, 2017. find
  12. R. E. Briscoe. Mental imagery and the varieties of amodal perception. Pacific Philosophical Quarterly, 92(2):153–173, 2011. find
  13. T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  14. R. Chandra, A. Bera, and D. Manocha. Stylepredict: Machine theory of mind for human driver behavior from trajectories. arXiv preprint arXiv:2011.04816, 2020. — [arXiv:2011.04816](https://arxiv.org/abs/2011.04816) find
  15. I. Clavera, J. Rothfuss, J. Schulman, Y. Fujita, T. Asfour, and P. Abbeel. Model-based reinforcement learning via meta-policy optimization. In Conference on Robot Learning, pages 617–629. PMLR, 2018. find
  16. R. Coulom. Efficient selectivity and backup operators in monte-carlo tree search. In Computers and Games: 5th International Conference, CG 2006, Turin, Italy, May 29-31, 2006. Revised Papers 5, pages 72–83. find
  17. I. Dasgupta, C. Kaeser-Chen, K. Marino, A. Ahuja, S. Babayan, F. Hill, and R. Fergus. Collaborating with language models for embodied reasoning. arXiv preprint arXiv:2302.00763, 2023.
  18. K. Dautenhahn. Socially intelligent robots: dimensions of human–robot interaction. Philosophical transactions of the royal society B: Biological sciences, 362(1480):679–704, 2007. find
  19. X. Deng, Y. Gu, B. Zheng, S. Chen, S. Stevens, B. Wang, H. Sun, and Y. Su. Mind2web: Towards a generalist agent for the web. arXiv preprint arXiv:2306.06070, 2023.
  20. N. Dziri, X. Lu, M. Sclar, X. L. Li, L. Jian, B. Y. Lin, P. West, C. Bhagavatula, R. L. Bras, J. D. Hwang, et al. Faith and fate: Limits of transformers on compositionality. arXiv preprint arXiv:2305.18654, 2023.
  21. A. Ermolov and N. Sebe. Latent world models for intrinsically motivated exploration. Advances in Neural Information Processing Systems, 33:5565–5575, 2020. find
  22. J. W. Forrester. Counterintuitive behavior of social systems. Theory and decision, 2(2):109–140, 1971. find
  23. D. Gentner and A. L. Stevens. Mental models. Psychology Press, 2014. find
  24. G. Gergely and G. Csibra. Teleological reasoning in infancy: The naıve theory of rational action. Trends in cognitive sciences, 7(7):287–292, 2003. find
  25. P. J. Gmytrasiewicz and P. Doshi. A framework for sequential planning in multi-agent settings. Journal of Artificial Intelligence Research, 24:49–79, 2005. find
  26. N. D. Goodman and M. C. Frank. Pragmatic language interpretation as probabilistic inference. Trends in cognitive sciences, 20(11):818–829, 2016. find
  27. Google. Gemini: A family of highly capable multimodal models. Technical report, Google, 2023.
  28. A. Gopnik and H. M. Wellman. The theory theory. In An earlier version of this chapter was presented at the Society for Research in Child Development Meeting, 1991. find
  29. Cambridge University Press, 1994. find
  30. N. Gothoskar, M. Cusumano-Towner, B. Zinberg, M. Ghavamizadeh, F. Pollok, A. Garrett, J. Tenenbaum, D. Gutfreund, and V. Mansinghka. 3dp3: 3d scene perception via probabilistic programming. Advances in Neural Information Processing Systems, 34:9600–9612, 2021. find
  31. D. Ha and J. Schmidhuber. World models. arXiv preprint arXiv:1803.10122, 2018. find
  32. D. Hadfield-Menell, S. J. Russell, P. Abbeel, and A. Dragan. Cooperative inverse reinforcement learning. In Advances in neural information processing systems, 2016. find
  33. D. Hafner, T. Lillicrap, I. Fischer, R. Villegas, D. Ha, H. Lee, and J. Davidson. Learning latent dynamics for planning from pixels. In International conference on machine learning, pages 2555–2565. PMLR, 2019.
  34. D. Hafner, T. Lillicrap, M. Norouzi, and J. Ba. Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193, 2020. find
  35. S. Hao, Y. Gu, H. Ma, J. J. Hong, Z. Wang, D. Z. Wang, and Z. Hu. Reasoning with Language Model is Planning with World Model. arXiv preprint arXiv:2305.14992, 2023a. find
  36. S. Hao, T. Liu, Z. Wang, and Z. Hu. Toolkengpt: Augmenting frozen language models with massive tools via tool embeddings. arXiv preprint arXiv:2305.11554, 2023b.
  37. A. Hu, L. Russell, H. Yeo, Z. Murez, G. Fedoseev, A. Kendall, J. Shotton, and G. Corrado. Gaia-1: A generative world model for autonomous driving. arXiv preprint arXiv:2309.17080, 2023. — [arXiv:2309.17080](https://arxiv.org/abs/2309.17080) find
  38. Z. Hu and E. P. Xing. Toward a ’Standard Model’ of Machine Learning. Harvard Data Science Review, 4(4), oct 27 2022. https://hdsr.mitpress.mit.edu/pub/zkib7xth. ↗
  39. W. Huang, P. Abbeel, D. Pathak, and I. Mordatch. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International Conference on Machine Learning, pages 9118–9147. PMLR, 2022.
  40. J. Jara-Ettinger, H. Gweon, L. E. Schulz, and J. B. Tenenbaum. The naïve utility calculus: Computational principles underlying commonsense psychology. Trends in cognitive sciences, 20(8): 589–604, 2016. find
  41. K. M. Jatavallabhula, M. Macklin, F. Golemo, V. Voleti, L. Petrini, M. Weiss, B. Considine, J. Parent-Lévesque, K. Xie, K. Erleben, et al. gradsim: Differentiable simulation for system identification and visuomotor control. arXiv preprint arXiv:2104.02646, 2021. — [arXiv:2104.02646](https://arxiv.org/abs/2104.02646) find
  42. K. Jha, T. A. Le, C. Jin, Y.-L. Kuo, J. B. Tenenbaum, and T. Shu. Neural amortized inference for nested multi-agent reasoning. arXiv preprint arXiv:2308.11071, 2023. — [arXiv:2308.11071](https://arxiv.org/abs/2308.11071) find
  43. C. Jin, Y. Wu, J. Cao, J. Xiang, Y.-L. Kuo, Z. Hu, T. Ullman, A. Torralba, J. Tenenbaum, and T. Shu. Mmtom-qa: Multimodal theory of mind question answering. In NeurIPS 2023 Foundation Models for Decision Making Workshop, 2023.
  44. P. N. Johnson-Laird. Mental models: Towards a cognitive science of language, inference, and consciousness. Harvard University Press, 1983. find
  45. P. N. Johnson-Laird. Mental models and human reasoning. PNAS, 2010. find
  46. J. Jung, L. Qin, S. Welleck, F. Brahman, C. Bhagavatula, R. L. Bras, and Y. Choi. Maieutic prompting: Logically consistent reasoning with recursive explanations. arXiv preprint arXiv:2205.11822, 2022.
  47. L. Kaiser, M. Babaeizadeh, P. Milos, B. Osinski, R. H. Campbell, K. Czechowski, D. Erhan, C. Finn, P. Kozakowski, S. Levine, et al. Model-based reinforcement learning for atari. arXiv preprint arXiv:1903.00374, 2019. find
  48. L. Kocsis and C. Szepesvári. Bandit based monte-carlo planning. In Machine Learning: ECML 2006: 17th European Conference on Machine Learning Berlin, Germany, September 18-22, 2006 Proceedings 17, pages 282–293. find
  49. M. Kwon, S. M. Xie, K. Bullard, and D. Sadigh. Reward design with language models. arXiv preprint arXiv:2303.00001, 2023.
  50. Y. LeCun. A path towards autonomous machine intelligence. Open Review, 2022. find
  51. B. Z. Li, M. Nye, and J. Andreas. Implicit representations of meaning in neural language models. arXiv preprint arXiv:2106.00737, 2021. find
  52. B. Z. Li, M. Nye, and J. Andreas. Language modeling with latent situations. arXiv preprint arXiv:2212.10012, 2022a. find
  53. S. Li, X. Puig, C. Paxton, Y. Du, C. Wang, L. Fan, T. Chen, D.-A. Huang, E. Akyürek, A. Anandkumar, et al. Pre-trained language models for interactive decision-making. Advances in Neural Information Processing Systems, 35:31199–31212, 2022b.
  54. Y. Li, H. He, J. Wu, D. Katabi, and A. Torralba. Learning compositional koopman operators for model-based control. arXiv preprint arXiv:1910.08264, 2019. — [arXiv:1910.08264](https://arxiv.org/abs/1910.08264) find
  55. Y. Li, T. Lin, K. Yi, D. Bear, D. Yamins, J. Wu, J. Tenenbaum, and A. Torralba. Visual grounding of learned physical models. In International conference on machine learning, pages 5927–5936. PMLR, 2020. find
  56. B. Liu, Y. Jiang, X. Zhang, Q. Liu, S. Zhang, J. Biswas, and P. Stone. Llm+ p: Empowering large language models with optimal planning proficiency. arXiv preprint arXiv:2304.11477, 2023a.
  57. H. Liu, C. Li, Q. Wu, and Y. J. Lee. Visual instruction tuning. arXiv preprint arXiv:2304.08485, 2023b.
  58. R. Liu, R. Yang, C. Jia, G. Zhang, D. Zhou, A. M. Dai, D. Yang, and S. Vosoughi. Training socially aligned language models in simulated human society. arXiv preprint arXiv:2305.16960, 2023c.
  59. Y. J. Ma, W. Liang, G. Wang, D.-A. Huang, O. Bastani, D. Jayaraman, Y. Zhu, L. Fan, and A. Anandkumar. Eureka: Human-level reward design via coding large language models. arXiv preprint arXiv:2310.12931, 2023.
  60. A. Madaan, N. Tandon, P. Gupta, S. Hallinan, L. Gao, S. Wiegreffe, U. Alon, N. Dziri, S. Prabhumoye, Y. Yang, et al. Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651, 2023. find
  61. Z. Mandi, S. Jain, and S. Song. Roco: Dialectic multi-robot collaboration with large language models. arXiv preprint arXiv:2307.04738, 2023. — [arXiv:2307.04738](https://arxiv.org/abs/2307.04738) find
  62. G. W. Maus, J. Fischer, and D. Whitney. Motion-dependent representation of space in area mt+. Neuron, 78(3):554–562, 2013. find
  63. T. M. Moerland, J. Broekens, A. Plaat, C. M. Jonker, et al. Model-based reinforcement learning: A survey. Foundations and Trends® in Machine Learning, 2023. find
  64. S. R. Moghaddam and C. J. Honey. Boosting theory-of-mind performance in large language models via prompting. arXiv preprint arXiv:2304.11490, 2023. — [arXiv:2304.11490](https://arxiv.org/abs/2304.11490) find
  65. N. Nortmann, S. Rekauzke, S. Onat, P. König, and D. Jancke. Primary visual cortex represents the difference between past and present. Cerebral Cortex, 25(6):1427–1440, 2015. find
  66. OpenAI. Chatgpt plugins. https://openai.com/blog/chatgpt-plugins, 2022. ↗
  67. OpenAI. Gpt-4 technical report, 2023.
  68. L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, et al. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744, 2022.
  69. S. Ouyang, Z. Zhang, B. Yan, X. Liu, J. Han, and L. Qin. Structured chemistry reasoning with large language models. arXiv preprint arXiv:2311.09656, 2023. — [arXiv:2311.09656](https://arxiv.org/abs/2311.09656) find
  70. B. Paranjape, S. Lundberg, S. Singh, H. Hajishirzi, L. Zettlemoyer, and M. T. Ribeiro. Art: Automatic multi-step reasoning and tool-use for large language models. arXiv preprint arXiv:2303.09014, 2023.
  71. J. S. Park, J. O’Brien, C. J. Cai, M. R. Morris, P. Liang, and M. S. Bernstein. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22, 2023. find
  72. M. Patel and S. Chernova. Proactive robot assistance via spatio-temporal object modeling. arXiv preprint arXiv:2211.15501, 2022. — [arXiv:2211.15501](https://arxiv.org/abs/2211.15501) find
  73. S. G. Patil, T. Zhang, X. Wang, and J. E. Gonzalez. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334, 2023.
  74. R. Pramod, M. Cohen, K. Lydic, J. Tenenbaum, and N. Kanwisher. Evidence that the brain’s physics engine runs forward simulations of what will happen next. Journal of Vision, 20(11):1521–1521, 2020. find
  75. D. Premack and G. Woodruff. Does the chimpanzee have a theory of mind? Behavioral and brain sciences, 1(4):515–526, 1978. find
  76. X. Puig, T. Shu, J. B. Tenenbaum, and A. Torralba. Nopa: Neurally-guided online probabilistic assistance for building socially intelligent home assistants. arXiv preprint arXiv:2301.05223, 2023. — [arXiv:2301.05223](https://arxiv.org/abs/2301.05223) find
  77. M. Sap, R. LeBras, D. Fried, and Y. Choi. Neural theory-of-mind? on the limits of social intelligence in large lms. arXiv preprint arXiv:2210.13312, 2022. find
  78. T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, L. Zettlemoyer, N. Cancedda, and T. Scialom. Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761, 2023.
  79. J. Schrittwieser, I. Antonoglou, T. Hubert, K. Simonyan, L. Sifre, S. Schmitt, A. Guez, E. Lockhart, D. Hassabis, T. Graepel, et al. Mastering atari, go, chess and shogi by planning with a learned model. Nature, 588(7839):604–609, 2020. find
  80. J. Schulkin. Action, perception and the brain: Adaptation and cephalic expression. Springer, 2012. find
  81. L. Schulz, N. Alon, J. S. Rosenschein, and P. Dayan. Emergent deception and skepticism via theory of mind. In ICML 2023: First Workshop on Theory of Mind in Communicating Agents (ToM 2023), 2023. find
  82. M. Sclar, G. Neubig, and Y. Bisk. Symmetric machine theory of mind. In K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvari, G. Niu, and S. Sabato, editors, Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 19450–19466. PM… find
  83. N. Shapira, M. Levy, S. H. Alavi, X. Zhou, Y. Choi, Y. Goldberg, M. Sap, and V. Shwartz. Clever hans or neural theory of mind? stress testing social reasoning in large language models. arXiv preprint arXiv:2305.14763, 2023. find
  84. N. Shinn, F. Cassano, A. Gopinath, K. R. Narasimhan, and S. Yao. Reflexion: Language agents with verbal reinforcement learning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  85. D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. Van Den Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, et al. Mastering the game of go with deep neural networks and tree search. nature, 529(7587):484–489, 2016. find
  86. K. Smith, L. Mei, S. Yao, J. Wu, E. Spelke, J. Tenenbaum, and T. Ullman. Modeling expectation violation in intuitive physics with coarse probabilistic object representations. Advances in neural information processing systems, 32, 2019. find
  87. E. S. Spelke and K. D. Kinzler. Core knowledge. Developmental science, 10(1):89–96, 2007. find
  88. T. Sumers, S. Yao, K. Narasimhan, and T. L. Griffiths. Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427, 2023. find
  89. R. Tejwani, Y.-L. Kuo, T. Shu, B. Katz, and A. Barbu. Social interactions as recursive mdps. In Conference on Robot Learning, pages 949–958. PMLR, 2022. find
  90. E. C. Tolman. Cognitive maps in rats and men. Psychological review, 55(4):189, 1948. find
  91. M. Toussaint. Learning a world model and planning with a self-organizing, dynamic neural system. Advances in neural information processing systems, 16, 2003. find
  92. M. A. Toussaint, K. R. Allen, K. A. Smith, and J. B. Tenenbaum. Differentiable physics and stable modes for tool-use and manipulation planning. 2018. find
  93. H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023a.
  94. H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, and Y. e. a. Babaei. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023b.
  95. T. Ullman. Large language models fail on trivial alterations to theory-of-mind tasks. arXiv preprint arXiv:2302.08399, 2023. find
  96. T. D. Ullman, E. Spelke, P. Battaglia, and J. B. Tenenbaum. Mind games: Game engines as an architecture for intuitive physics. Trends in cognitive sciences, 21(9):649–665, 2017. find
  97. G. Wang, Y. Xie, Y. Jiang, A. Mandlekar, C. Xiao, Y. Zhu, L. Fan, and A. Anandkumar. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291, 2023a. find
  98. Q. Wang, K. Saha, E. Gregori, D. Joyner, and A. Goel. Towards mutual theory of mind in human-ai interaction: How language reflects what students perceive about a virtual teaching assistant. In Proceedings of the 2021 CHI conference on human factors in computing systems, pages 1–14, 2021. find
  99. X. Wang, C. Li, Z. Wang, F. Bai, H. Luo, J. Zhang, N. Jojic, E. P. Xing, and Z. Hu. Promptagent: Strategic planning with language models enables expert-level prompt optimization. arXiv preprint arXiv:2310.16427, 2023b.
  100. X. Wang, Z. Wang, J. Liu, Y. Chen, L. Yuan, H. Peng, and H. Ji. Mint: Evaluating llms in multi-turn interaction with tools and language feedback. arXiv preprint arXiv:2309.10691, 2023c.
  101. Z. Wang, S. Cai, A. Liu, X. Ma, and Y. Liang. Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. arXiv preprint arXiv:2302.01560, 2023d.
  102. J. Wei, X. Wang, D. Schuurmans, M. Bosma, E. Chi, Q. Le, and D. Zhou. Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903, 2022.
  103. Y. Weng, M. Zhu, S. He, K. Liu, and J. Zhao. Large language models are reasoners with self-verification. arXiv preprint arXiv:2212.09561, 2022.
  104. L. Wong, G. Grand, A. K. Lew, N. D. Goodman, V. K. Mansinghka, J. Andreas, and J. B. Tenenbaum. From word models to world models: Translating from natural language to the probabilistic language of thought. 2023. find
  105. J. Wu, E. Lu, P. Kohli, B. Freeman, and J. Tenenbaum. Learning to see physics via visual de-animation. NeurIPS, 2017. find
  106. J. Xiang, T. Tao, Y. Gu, T. Shu, Z. Wang, Z. Yang, and Z. Hu. Language Models Meet World Models: Embodied Experiences Enhance Language Models. arXiv preprint arXiv:2305.10626, 2023. find
  107. Y. Xie, K. Kawaguchi, Y. Zhao, X. Zhao, M.-Y. Kan, J. He, and Q. Xie. Decomposition enhances reasoning via self-evaluation guided decoding. arXiv preprint arXiv:2305.00633, 2023a.
  108. Y. Xie, C. Yu, T. Zhu, J. Bai, Z. Gong, and H. Soh. Translating natural language to planning goals with large-language models. arXiv preprint arXiv:2302.05128, 2023b. — [arXiv:2302.05128](https://arxiv.org/abs/2302.05128) find
  109. M. Yang, Y. Du, K. Ghasemipour, J. Tompson, D. Schuurmans, and P. Abbeel. Learning interactive real-world simulators. arXiv preprint arXiv:2310.06114, 2023.
  110. S. Yao, D. Yu, J. Zhao, I. Shafran, T. L. Griffiths, Y. Cao, and K. Narasimhan. Tree of thoughts: Deliberate problem solving with large language models. 2023a. find
  111. S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao. ReAct: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR), 2023b.
  112. W. Yu, N. Gileadi, C. Fu, S. Kirmani, K.-H. Lee, M. G. Arenas, H.-T. L. Chiang, T. Erez, L. Hasenclever, J. Humplik, et al. Language to rewards for robotic skill synthesis. arXiv preprint arXiv:2306.08647, 2023. — [arXiv:2306.08647](https://arxiv.org/abs/2306.08647) find
  113. A. Zeng, M. Liu, R. Lu, B. Wang, X. Liu, Y. Dong, and J. Tang. Agenttuning: Enabling generalized agent abilities for llms. arXiv preprint arXiv:2310.12823, 2023.
  114. H. Zhang, W. Du, J. Shan, Q. Zhou, Y. Du, J. B. Tenenbaum, T. Shu, and C. Gan. Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485, 2023.
  115. M. Zhang, S. Vikram, L. Smith, P. Abbeel, M. Johnson, and S. Levine. Solar: Deep structured representations for model-based reinforcement learning. In International conference on machine learning, pages 7444–7453. PMLR, 2019. find
  116. T. Zhi-Xuan, J. Mann, T. Silver, J. Tenenbaum, and V. Mansinghka. Online bayesian goal inference for boundedly rational planning agents. Advances in neural information processing systems, 33: 19238–19250, 2020. find
  117. D. Zhou, N. Schärli, L. Hou, J. Wei, N. Scales, X. Wang, D. Schuurmans, O. Bousquet, Q. Le, and E. Chi. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625, 2022.
  118. X. Zhu, J. Wang, L. Zhang, Y. Zhang, R. Gan, J. Zhang, and Y. Yang. Solving math word problem via cooperative reasoning induced language models. arXiv preprint arXiv:2210.16257, 2022.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hu-2023-language-models-agent-models-world/