Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models (2405.18208v1)

Published 28 May 2024 in cs.AI, cs.CL, and cs.LG

Abstract: Recent studies have highlighted their proficiency in some simple tasks like writing and coding through various reasoning strategies. However, LLM agents still struggle with tasks that require comprehensive planning, a process that challenges current models and remains a critical research issue. In this study, we concentrate on travel planning, a Multi-Phases planning problem, that involves multiple interconnected stages, such as outlining, information gathering, and planning, often characterized by the need to manage various constraints and uncertainties. Existing reasoning approaches have struggled to effectively address this complex task. Our research aims to address this challenge by developing a human-like planning framework for LLM agents, i.e., guiding the LLM agent to simulate various steps that humans take when solving Multi-Phases problems. Specifically, we implement several strategies to enable LLM agents to generate a coherent outline for each travel query, mirroring human planning patterns. Additionally, we integrate Strategy Block and Knowledge Block into our framework: Strategy Block facilitates information collection, while Knowledge Block provides essential information for detailed planning. Through our extensive experiments, we demonstrate that our framework significantly improves the planning capabilities of LLM agents, enabling them to tackle the travel planning task with improved efficiency and effectiveness. Our experimental results showcase the exceptional performance of the proposed framework; when combined with GPT-4-Turbo, it attains $10\times$ the performance gains in comparison to the baseline framework deployed on GPT-4-Turbo.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
  2. Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning, pages 337–371. PMLR, 2023.
  3. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 17682–17690, 2024.
  4. Emergent autonomous scientific research capabilities of large language models. arXiv preprint arXiv:2304.05332, 2023.
  5. Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:2304.05376, 2023.
  6. Autoagents: A framework for automatic agent generation. arXiv preprint arXiv:2309.17288, 2023.
  7. Binding language models in symbolic languages. arXiv preprint arXiv:2210.02875, 2022.
  8. Dynamic planning with a llm. arXiv preprint arXiv:2308.06391, 2023.
  9. Collaborating with language models for embodied reasoning. arXiv preprint arXiv:2302.00763, 2023.
  10. Human-level play in the game of diplomacy by combining language models with strategic reasoning. Science, 378(6624):1067–1074, 2022.
  11. Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation. arXiv preprint arXiv:2401.02117, 2024.
  12. S3: Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv:2307.14984, 2023.
  13. Critic: Large language models can self-correct with tool-interactive critiquing. arXiv preprint arXiv:2305.11738, 2023.
  14. 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.
  15. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680, 2024.
  16. Reasoning with language model is planning with world model. arXiv preprint arXiv:2305.14992, 2023.
  17. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023.
  18. Agentcoder: Multi-agent-based code generation with iterative testing and optimisation. arXiv preprint arXiv:2312.13010, 2023.
  19. Recommender ai agent: Integrating large language models for interactive recommendations. arXiv preprint arXiv:2308.16505, 2023.
  20. Understanding the planning of llm agents: A survey. arXiv preprint arXiv:2402.02716, 2024.
  21. Mistral 7b. arXiv preprint arXiv:2310.06825, 2023.
  22. Mixtral of experts. arXiv preprint arXiv:2401.04088, 2024.
  23. Swe-bench: Can language models resolve real-world github issues? arXiv preprint arXiv:2310.06770, 2023.
  24. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474, 2020.
  25. Camel: Communicative agents for" mind" exploration of large scale language model society. 2023.
  26. Large language model-empowered agents for simulating macroeconomic activities. arXiv preprint arXiv:2310.10436, 2023.
  27. Tradinggpt: Multi-agent system with layered memory and distinct characters for enhanced financial trading performance. arXiv preprint arXiv:2309.03736, 2023.
  28. Llm+ p: Empowering large language models with optimal planning proficiency. arXiv preprint arXiv:2304.11477, 2023.
  29. Think-in-memory: Recalling and post-thinking enable llms with long-term memory. arXiv preprint arXiv:2311.08719, 2023.
  30. Llava-plus: Learning to use tools for creating multimodal agents. arXiv preprint arXiv:2311.05437, 2023.
  31. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36, 2024.
  32. Generation-augmented retrieval for open-domain question answering. arXiv preprint arXiv:2009.08553, 2020.
  33. Welfare diplomacy: Benchmarking language model cooperation. arXiv preprint arXiv:2310.08901, 2023.
  34. Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730–27744, 2022.
  35. Talm: Tool augmented language models. arXiv preprint arXiv:2205.12255, 2022.
  36. 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.
  37. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334, 2023.
  38. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023.
  39. Tool learning with foundation models. arXiv preprint arXiv:2304.08354, 2023.
  40. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36, 2024.
  41. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems, 36, 2024.
  42. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36, 2024.
  43. Vipergpt: Visual inference via python execution for reasoning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 11888–11898, 2023.
  44. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023.
  45. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291, 2023.
  46. Avalon’s game of thoughts: Battle against deception through recursive contemplation. arXiv preprint arXiv:2310.01320, 2023.
  47. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171, 2022.
  48. What are tools anyway? a survey from the language model perspective. arXiv preprint arXiv:2403.15452, 2024.
  49. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022.
  50. Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671, 2023.
  51. Smartplay: A benchmark for llms as intelligent agents. arXiv preprint arXiv:2310.01557, 2023.
  52. Llm a*: Human in the loop large language models enabled a* search for robotics. arXiv preprint arXiv:2312.01797, 2023.
  53. Can large language model agents simulate human trust behaviors? arXiv preprint arXiv:2402.04559, 2024.
  54. Travelplanner: A benchmark for real-world planning with language agents. arXiv preprint arXiv:2402.01622, 2024.
  55. Language agents with reinforcement learning for strategic play in the werewolf game. arXiv preprint arXiv:2310.18940, 2023.
  56. Gpt4tools: Teaching large language model to use tools via self-instruction. Advances in Neural Information Processing Systems, 36, 2024.
  57. Coupling large language models with logic programming for robust and general reasoning from text. arXiv preprint arXiv:2307.07696, 2023.
  58. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36, 2024.
  59. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629, 2022.
  60. Easytool: Enhancing llm-based agents with concise tool instruction. arXiv preprint arXiv:2401.06201, 2024.
  61. Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485, 2023.
  62. Competeai: Understanding the competition behaviors in large language model-based agents. arXiv preprint arXiv:2310.17512, 2023.
  63. Large language models as commonsense knowledge for large-scale task planning. Advances in Neural Information Processing Systems, 36, 2024.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Chengxing Xie (10 papers)
  2. Difan Zou (71 papers)
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets