Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the Roles of LLMs in Planning: Embedding LLMs into Planning Graphs (2403.00783v2)

Published 18 Feb 2024 in cs.AI

Abstract: Plan synthesis aims to generate a course of actions or policies to transit given initial states to goal states, provided domain models that could be designed by experts or learnt from training data or interactions with the world. Intrigued by the claims of emergent planning capabilities in LLMs, works have been proposed to investigate the planning effectiveness of LLMs, without considering any utilization of off-the-shelf planning techniques in LLMs. In this paper, we aim to further study the insight of the planning capability of LLMs by investigating the roles of LLMs in off-the-shelf planning frameworks. To do this, we investigate the effectiveness of embedding LLMs into one of the well-known planning frameworks, graph-based planning, proposing a novel LLMs-based planning framework with LLMs embedded in two levels of planning graphs, i.e., mutual constraints generation level and constraints solving level. We empirically exhibit the effectiveness of our proposed framework in various planning domains.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Learning action models with minimal observability. Artif. Intell., 275:104–137, 2019. doi: 10.1016/J.ARTINT.2019.05.003. URL https://doi.org/10.1016/j.artint.2019.05.003.
  2. Compositional foundation models for hierarchical planning. CoRR, abs/2309.08587, 2023.
  3. Fast planning through planning graph analysis. Artif. Intell., 90(1-2):281–300, 1997.
  4. RT-1: robotics transformer for real-world control at scale. In Bekris, K. E., Hauser, K., Herbert, S. L., and Yu, J. (eds.), Robotics: Science and Systems XIX, Daegu, Republic of Korea, July 10-14, 2023, 2023.
  5. Palm: Scaling language modeling with pathways. J. Mach. Learn. Res., 24:240:1–240:113, 2023.
  6. Palm-e: An embodied multimodal language model. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Research, pp.  8469–8488. PMLR, 2023.
  7. STRIPS: A new approach to the application of theorem proving to problem solving. Artif. Intell., 2(3/4):189–208, 1971. doi: 10.1016/0004-3702(71)90010-5. URL https://doi.org/10.1016/0004-3702(71)90010-5.
  8. LPG: A planner based on local search for planning graphs with action costs. In Ghallab, M., Hertzberg, J., and Traverso, P. (eds.), Proceedings of the Sixth International Conference on Artificial Intelligence Planning Systems, April 23-27, 2002, Toulouse, France, pp. 13–22. AAAI, 2002. URL http://www.aaai.org/Library/AIPS/2002/aips02-002.php.
  9. Pddl - the planning domain definition language. 08 1998.
  10. Automated Planning: Theory and Practice. Morgan Kaufmann, 2004.
  11. Reasoning with language model is planning with world model. In Bouamor, H., Pino, J., and Bali, K. (eds.), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pp.  8154–8173. Association for Computational Linguistics, 2023. URL https://aclanthology.org/2023.emnlp-main.507.
  12. Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. In Rogers, A., Boyd-Graber, J. L., and Okazaki, N. (eds.), Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pp.  8003–8017. Association for Computational Linguistics, 2023. doi: 10.18653/V1/2023.FINDINGS-ACL.507. URL https://doi.org/10.18653/v1/2023.findings-acl.507.
  13. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In Chaudhuri, K., Jegelka, S., Song, L., Szepesvári, C., Niu, G., and Sabato, S. (eds.), International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pp.  9118–9147. PMLR, 2022a. URL https://proceedings.mlr.press/v162/huang22a.html.
  14. Inner monologue: Embodied reasoning through planning with language models. In Conference on Robot Learning, CoRL 2022, 14-18 December 2022, Auckland, New Zealand, volume 205 of Proceedings of Machine Learning Research, pp.  1769–1782. PMLR, 2022b.
  15. Do as I can, not as I say: Grounding language in robotic affordances. In Conference on Robot Learning, CoRL 2022, 14-18 December 2022, Auckland, New Zealand, volume 205 of Proceedings of Machine Learning Research, pp.  287–318. PMLR, 2022. URL https://proceedings.mlr.press/v205/ichter23a.html.
  16. Gradient-based mixed planning with symbolic and numeric action parameters. Artif. Intell., 313:103789, 2022a. doi: 10.1016/j.artint.2022.103789. URL https://doi.org/10.1016/j.artint.2022.103789.
  17. Creativity of AI: automatic symbolic option discovery for facilitating deep reinforcement learning. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pp.  7042–7050. AAAI Press, 2022b. doi: 10.1609/AAAI.V36I6.20663. URL https://doi.org/10.1609/aaai.v36i6.20663.
  18. Learning to act for perceiving in partially unknown environments. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China, pp.  5485–5493. ijcai.org, 2023. doi: 10.24963/IJCAI.2023/609. URL https://doi.org/10.24963/ijcai.2023/609.
  19. Pre-trained language models for interactive decision-making. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022.
  20. Less is more: Task-aware layer-wise distillation for language model compression. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Research, pp.  20852–20867. PMLR, 2023. URL https://proceedings.mlr.press/v202/liang23j.html.
  21. LLM+P: empowering large language models with optimal planning proficiency. CoRR, abs/2304.11477, 2023. doi: 10.48550/ARXIV.2304.11477. URL https://doi.org/10.48550/arXiv.2304.11477.
  22. Chameleon: Plug-and-play compositional reasoning with large language models. CoRR, abs/2304.09842, 2023.
  23. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022.
  24. Plansformer tool: Demonstrating generation of symbolic plans using transformers. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China, pp.  7158–7162. ijcai.org, 2023.
  25. Planning with large language models via corrective re-prompting. CoRR, abs/2211.09935, 2022. doi: 10.48550/ARXIV.2211.09935. URL https://doi.org/10.48550/arXiv.2211.09935.
  26. A generalist agent. Trans. Mach. Learn. Res., 2022, 2022.
  27. Hugginggpt: Solving AI tasks with chatgpt and its friends in huggingface. CoRR, abs/2303.17580, 2023.
  28. Reflexion: an autonomous agent with dynamic memory and self-reflection. CoRR, abs/2303.11366, 2023.
  29. Distilling reasoning capabilities into smaller language models. In Rogers, A., Boyd-Graber, J. L., and Okazaki, N. (eds.), Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pp.  7059–7073. Association for Computational Linguistics, 2023. doi: 10.18653/V1/2023.FINDINGS-ACL.441. URL https://doi.org/10.18653/v1/2023.findings-acl.441.
  30. Generalized planning in PDDL domains with pretrained large language models. CoRR, abs/2305.11014, 2023.
  31. Adaplanner: Adaptive planning from feedback with language models. In NeurIPS, 2023.
  32. Llama: Open and efficient foundation language models. CoRR, abs/2302.13971, 2023. doi: 10.48550/ARXIV.2302.13971. URL https://doi.org/10.48550/arXiv.2302.13971.
  33. Leveraging pre-trained large language models to construct and utilize world models for model-based task planning. In NeurIPS, 2023a.
  34. On the planning abilities of large language models : A critical investigation. In NeurIPS, 2023b.
  35. Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. CoRR, abs/2302.01560, 2023.
  36. Chain-of-thought prompting elicits reasoning in large language models. In Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., and Oh, A. (eds.), Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022.
  37. Tree of thoughts: Deliberate problem solving with large language models. CoRR, abs/2305.10601, 2023a.
  38. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023b. URL https://openreview.net/pdf?id=WE_vluYUL-X.
  39. Planning with large language models for code generation. CoRR, abs/2303.05510, 2023. doi: 10.48550/ARXIV.2303.05510. URL https://doi.org/10.48550/arXiv.2303.05510.
  40. Large language models as commonsense knowledge for large-scale task planning. CoRR, abs/2305.14078, 2023.
  41. Zhuo, H. H. Crowdsourced action-model acquisition for planning. In AAAI, pp.  3439–3446, 2015.
  42. Model-lite planning: Case-based vs. model-based approaches. Artif. Intell., 246:1–21, 2017. doi: 10.1016/j.artint.2017.01.004. URL https://doi.org/10.1016/j.artint.2017.01.004.
  43. Cross-domain action-model acquisition for planning via web search. In Bacchus, F., Domshlak, C., Edelkamp, S., and Helmert, M. (eds.), Proceedings of the 21st International Conference on Automated Planning and Scheduling, ICAPS 2011, Freiburg, Germany June 11-16, 2011. AAAI, 2011. URL http://aaai.org/ocs/index.php/ICAPS/ICAPS11/paper/view/2678.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Hankz Hankui Zhuo (35 papers)
  2. Xin Chen (456 papers)
  3. Rong Pan (33 papers)