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

Planning with Multi-Constraints via Collaborative Language Agents (2405.16510v4)

Published 26 May 2024 in cs.AI, cs.CL, and cs.LG

Abstract: The rapid advancement of neural LLMs has sparked a new surge of intelligent agent research. Unlike traditional agents, LLM-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning and generalization capabilities. Effective planning is crucial for the success of LLM agents in real-world tasks, making it a highly pursued topic in the community. Current planning methods typically translate tasks into executable action sequences. However, determining a feasible or optimal sequence for complex tasks with multiple constraints at fine granularity, which often requires compositing long chains of heterogeneous actions, remains challenging. This paper introduces Planning with Multi-Constraints (PMC), a zero-shot methodology for collaborative LLM-based multi-agent systems that simplifies complex task planning with constraints by decomposing it into a hierarchy of subordinate tasks. Each subtask is then mapped into executable actions. PMC was assessed on two constraint-intensive benchmarks, TravelPlanner and API-Bank. Notably, PMC achieved an average 42.68% success rate on TravelPlanner, significantly higher than GPT-4 (2.92%), and outperforming GPT-4 with ReAct on API-Bank by 13.64%, showing the immense potential of integrating LLM with multi-agent systems. We also show that PMC works with small LLM as the planning core, e.g., LLaMA-3.1-8B.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (67)
  1. Understanding the planning of llm agents: A survey. ArXiv, abs/2402.02716, 2024.
  2. Michael Wooldridge. Intelligent agents. Multiagent systems: A modern approach to distributed artificial intelligence, 1:27–73, 1999.
  3. Dominic Wong. A critical literature review on e-learning limitations. Journal for the Advancement of Science and Arts, 2(1):55–62, 2007.
  4. Reinforcement learning: An introduction. MIT press, 2018.
  5. Deep reinforcement learning: A survey. IEEE Transactions on Neural Networks and Learning Systems, 2022.
  6. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6):1–26, 2024.
  7. How far are we from agi. In ICLR 2024 Workshops, 2024.
  8. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems, 36, 2024.
  9. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2609–2634, Toronto, Canada, July 2023. Association for Computational Linguistics.
  10. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022.
  11. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, 2023.
  12. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. Transactions on Machine Learning Research, 2023.
  13. Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671, 2023.
  14. PAL: Program-aided language models. In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 10764–10799. PMLR, 23–29 Jul 2023.
  15. Managing heterogeneous multi-system tasks to support enterprise-wide operations. Distributed and Parallel Databases, 3:155–186, 1995.
  16. Dynamic planning with a llm. arXiv preprint arXiv:2308.06391, 2023.
  17. Leveraging pre-trained large language models to construct and utilize world models for model-based task planning. Advances in Neural Information Processing Systems, 36:79081–79094, 2023.
  18. Coupling large language models with logic programming for robust and general reasoning from text. In The 61st Annual Meeting Of The Association For Computational Linguistics, 2023.
  19. Jon Barwise. An introduction to first-order logic. In Studies in Logic and the Foundations of Mathematics, volume 90, pages 5–46. Elsevier, 1977.
  20. Inductive logic programming at 30: a new introduction. Journal of Artificial Intelligence Research, 74:765–850, 2022.
  21. Camel: Communicative agents for" mind" exploration of large language model society. Advances in Neural Information Processing Systems, 36, 2024.
  22. 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.
  23. Large language models empowered agent-based modeling and simulation: A survey and perspectives. arXiv preprint arXiv:2312.11970, 2023.
  24. Progprompt: Generating situated robot task plans using large language models. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 11523–11530. IEEE, 2023.
  25. Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157, 2024.
  26. Travelplanner: A benchmark for real-world planning with language agents. ArXiv, abs/2402.01622, 2024.
  27. API-bank: A comprehensive benchmark for tool-augmented LLMs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3102–3116, Singapore, December 2023. Association for Computational Linguistics.
  28. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  29. Eur Ing Albert Lester. Chapter 20 - planning blocks and subdivision of blocks. In Eur Ing Albert Lester, editor, Project Management, Planning and Control (Seventh Edition), pages 131–142. Butterworth-Heinemann, seventh edition edition, 2017.
  30. A survey of chain of thought reasoning: Advances, frontiers and future. ArXiv, abs/2309.15402, 2023.
  31. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6), March 2024.
  32. The landscape of emerging ai agent architectures for reasoning, planning, and tool calling: A survey. ArXiv, abs/2404.11584, 2024.
  33. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems, volume 35, pages 22199–22213. Curran Associates, Inc., 2022.
  34. Chain-of-thought prompting elicits reasoning in large language models. ArXiv, abs/2201.11903, 2023.
  35. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, 2023.
  36. Tree of thoughts: Deliberate problem solving with large language models. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  37. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, page 17682–17690. Association for the Advancement of Artificial Intelligence (AAAI), March 2024.
  38. Wizardlm: Empowering large language models to follow complex instructions. ArXiv, abs/2304.12244, 2023.
  39. Self-instruct: Aligning language models with self-generated instructions. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13484–13508, Toronto, Canada, July 2023. Association for Computational Linguistics.
  40. Self-evaluation improves selective generation in large language models. ArXiv, abs/2312.09300, 2023.
  41. Toolformer: Language models can teach themselves to use tools. arXiv, abs/2302.04761, 2023.
  42. Gpt4tools: Teaching large language model to use tools via self-instruction. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems, volume 36, pages 71995–72007. Curran Associates, Inc., 2023.
  43. Planning in the brain. Neuron, 110(6):914–934, 2022.
  44. Llm a*: Human in the loop large language models enabled a* search for robotics. ArXiv, abs/2312.01797, 2023.
  45. Reflexion: Language agents with verbal reinforcement learning. ArXiv, abs/2303.11366, 2023.
  46. Self-refine: Iterative refinement with self-feedback. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  47. Inner monologue: Embodied reasoning through planning with language models. ArXiv, abs/2207.05608, 2022.
  48. CRITIC: Large language models can self-correct with tool-interactive critiquing. In The Twelfth International Conference on Learning Representations, 2024.
  49. Llm+p: Empowering large language models with optimal planning proficiency. ArXiv, abs/2304.11477, 2023.
  50. Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks. In Advances in Neural Information Processing Systems, volume 36, pages 23813–23825. Curran Associates, Inc., 2023.
  51. Expel: Llm agents are experiential learners. Proceedings of the AAAI Conference on Artificial Intelligence, 38(17):19632–19642, Mar. 2024.
  52. The rise and potential of large language model based agents: A survey. ArXiv, abs/2309.07864, 2023.
  53. Webshop: Towards scalable real-world web interaction with grounded language agents. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems, volume 35, pages 20744–20757. Curran Associates, Inc., 2022.
  54. Mind2web: Towards a generalist agent for the web. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems, volume 36, pages 28091–28114. Curran Associates, Inc., 2023.
  55. A real-world webagent with planning, long context understanding, and program synthesis. In The Twelfth International Conference on Learning Representations, 2024.
  56. Exposing limitations of language model agents in sequential-task compositions on the web. In ICLR 2024 Workshop on Large Language Model (LLM) Agents, 2024.
  57. Easytool: Enhancing llm-based agents with concise tool instruction. ArXiv, abs/2401.06201, 2024.
  58. Sciagent: Tool-augmented language models for scientific reasoning. ArXiv, abs/2402.11451, 2024.
  59. Chameleon: Plug-and-play compositional reasoning with large language models. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  60. Language agent tree search unifies reasoning acting and planning in language models. ArXiv, abs/2310.04406, 2023.
  61. Reason for future, act for now: A principled framework for autonomous llm agents with provable sample efficiency. ArXiv, abs/2309.17382, 2023.
  62. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors. In The Twelfth International Conference on Learning Representations, 2024.
  63. MetaGPT: Meta programming for a multi-agent collaborative framework. In The Twelfth International Conference on Learning Representations, 2024.
  64. Mindagent: Emergent gaming interaction. ArXiv, abs/2309.09971, 2023.
  65. Aios: Llm agent operating system. ArXiv, abs/2403.16971, 2024.
  66. Language agents as optimizable graphs. arXiv preprint arXiv:2402.16823, 2024.
  67. Large language models as optimizers. In The Twelfth International Conference on Learning Representations, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Cong Zhang (121 papers)
  2. Dexun Li (15 papers)
  3. Hao Zhang (947 papers)
  4. Yong Liu (721 papers)
  5. Derrick Goh Xin Deik (4 papers)
Citations (1)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets