Survey on Intelligent Planning Methods from Large Language Models Perspective

doi:10.16182/j.issn1004731x.joss.23-1468

Abstract

Abstract:

. Starting from the perspective of large language models, this paper gives an overview of the definition and development of intelligent planning, and briefly introduces the traditional methods of intelligent planning; based on the close relationship between large language model intelligent agents and intelligent planning, introduces the architecture of large language models and typical large model intelligent agents; focusing on the intelligent planning for large language models, combs through the learning of planning languages, chain of thought, feedback optimization, and process automation; combining with the current challenges and difficulties, introduces the outlook of cutting-edge research on intelligent planning with large models.

Key words: intelligent planning, large language models, generative intelligence, chain of thought

CLC Number:

TP391

Zhou Yanzhong, Luo Junren, Gu Xueqiang, Zhang Wanpeng. Survey on Intelligent Planning Methods from Large Language Models Perspective[J]. Journal of System Simulation, 2025, 37(4): 823-844.

Figures/Tables 13

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Table 1

Planning methods based on large language model

方法	名称	特点
规划语言学习	LLM-P^[50]	将经典规划器的优势融入到LLM框架中，实现用户用自然语言进行任务规划领域建模
	LLM-DP^[51]	利用LLM将观测值、当前世界状态和目标状态转换为PDDL，使其能够完整且准确地表示规划问题
	CO-LLM^[52]	结合外部低级规划器来有效地执行基于高层次规划的操作
	LLM-Planner^[53]	当在任务完成过程中遇到对象不匹配和无法实现的规划结果时，该算法会动态更新LLM生成的规划结果
思维推理	CoT^[54]	模仿人类思考的过程，给出逐步解决问题的依据，将一个多步问题分解为多个可被单独解答的中间步骤
	零样本CoT^[55]	不需要构建思维链的演示样例，减少了人工成本
	CoT-SC^[56]	进行分步骤思考的过程中采样生成不同的思维链，获取多个答案结果，通过投票机制选取最终结果
	ToT^[57]	分解问题进行规划的过程中使用树状结构生成规划的步骤
	RecMind^[58]	利用自我启发机制，将在思维树的规划过程中被丢弃的一些历史步骤利用起来
	GoT^[59]	将思维树中的树状分解结构扩展为图结构
	AoT^[60]	将算法示例合并到提示中
	DAG推理^[61]	通过有向无环图对思维过程进行更一般性的建模
	XoT^[62]	可以探索不同的思维结构，如链、树、图等
	SoT^[63]	生成答案的骨架，进行并行工具调用或分批解码，并行完成每个骨架点的内容
	PoT^[64]	通过大语言模型不仅生成推理问题的答案，而且生成能够反映推理逻辑的程序代码
	JUDEC^[65]	采用基于Elo的评分机制给思维步骤进行打分判定
反馈优化	ReAct^[66]	使用思维-行动-观察三元组构建提示，思想组件旨在促进高级规划和规划，从而指导行为
	Voyager^[45]	结合了环境反馈、执行错误，以及自我验证3种反馈
	Ghost^[67]	将环境状态以及每个执行动作的成功或者失败信息作为反馈
	SayPlan^[68]	利用来自场景图模拟器的环境反馈来验证和完善其规划结果
	DEPS^[69]	告知任务失败的详细原因，有助于在长期规划过程中更好地从反馈中纠正错误
	Inner Monologue^[70]	主动征求用户关于外部场景描述的反馈意见，将用户的反馈意见作为提示输入
	Self-Refine^[71]	输出结果，然后收到反馈进行迭代优化，直到达到用户满意的规划结果
	Self-Check^[72]	对智能体在各个阶段生成的规划结果进行检查和评估，纠正在规划过程中的错误
	InterAct^[73]	使用不同的语言模型对规划的结果进行检查和排序，帮助主要语言模型避免错误和低效的操作
	Reflexion^[74]	提出了一种不通过更新权重，而是通过语言反馈来增强大模型的模型框架
流程自动化	LangChain^[75][76]	大语言模型与外部计算和数据源相结合，通过组件的方式构建遵循一般流程的语言模型应用程序
	HuggingGPT^[77]	让大语言模型充当一个控制器来管理现有的AI模型，解决复杂的AI任务
	低代码LLM^[78]	通过6种简单的低代码可视化编程交互，包括支持点击、拖动或文本编辑等，用户可以通过交互操作将自己的想法融入规划流程
	MetaGPT^[79]	将SOP编码为提示，让智能体生成规范化的设计文档、接口等，明确角色责任、提高协作质量
	自动化智能体框架^[80]	把智能体的状态抽象为状态类
	Prompt Flow^[81]	简化基于LLM的应用程序的端到端开发流程，使提示工程变得更加容易，使用户能够构建具有更高质量的LLM应用程序
	RAP-LLM^[82][83]	大模型通过自然语言处理技术将用户需求转换为RPA领域的表述，同时生成自动化流程，完成之后，RPA执行既定方案，完成业务流程自动化闭环
	ProAgent^[84]	结合大模型智能体帮助人类进行工作流构建，并让智能体自主处理工作流中涉及复杂决策与动态处理的环节

Table 1

References 99

1	Fikes R E, Nilsson N J. Strips: A New Approach to the Application of Theorem Proving to Problem Solving[J]. Artificial Intelligence, 1971, 2(3/4): 189-208.
2	Kase S E, Hung C P, Krayzman T, et al. The Future of Collaborative Human-artificial Intelligence Decision-making for Mission Planning[J]. Frontiers in Psychology, 2022, 13: 850628.
3	Shanahan M. Talking About Large Language Models[J]. Communications of the ACM, 2024, 67(2): 68-79.
4	Bonet Blai, Geffner Héctor. Planning as Heuristic Search[J]. Artificial Intelligence, 2001, 129(1/2): 5-33.
5	Laborie Philippe. Algorithms for Propagating Resource Constraints in AI Planning and Scheduling: Existing Approaches and New Results[J]. Artificial Intelligence, 2003, 143(2): 151-188.
6	Cross S E, Walker E. Dart: Applying Knowledge-based Planning and Scheduling to Crisis Action Planning[J]. Intelligent scheduling, 1994, 25:711-729.
7	张万鹏, 王楠, 陈璟. 一种利用工作流模型的分层任务网络规划领域建模方法[J]. 智能系统学报, 2011, 6(3): 239-247.
	Zhang Wanpeng, Wang Nan, Chen Jing. An HTN Planning Domain Modeling Method Using a Workflow Model[J]. CAAI Transactions on Intelligent Systems, 2011, 6(3): 239-247.
8	Weld D S. Recent Advances in AI Planning[J]. AI Magazine, 1999, 20(2): 93-123.
9	Newell A, Simon H A. GPS, a Program that Simulates Human Thought [C]//Computation & Intelligence: Collected Readings. USA: American Association for Artificial Intelligence, 1995: 415 - 428
10	Green C. Theorem-proving by Resolution as a Basis for Question-answering Systems[J]. Machine Intelligence, 1969, 4: 183-205.
11	Bylander T. The Computational Complexity of Propositional STRIPS Planning[J]. Artificial Intelligence, 1994, 69(1/2): 165-204.
12	Borrajo Daniel, Veloso M. Lazy Incremental Learning of Control Knowledge for Efficiently Obtaining Quality Plans[J]. Artificial Intelligence Review, 1997, 11(1): 371-405.
13	Cohen W W. Abductive Explanation-based Learning: A Solution to the Multiple Inconsistent Explanation Problem[J]. Machine Learning, 1992, 8(2): 167-219.
14	Aler Ricardo, Borrajo Daniel, Isasi Pedro. Genetic Programming and Deductive-inductive Learning: A Multi-strategy Approach[C]//Proceedings of the Fifteenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers Inc., 1998: 10-18.
15	Tomás de la Rosa, Jiménez Sergio, Borrajo Daniel. Learning Relational Decision Trees for Guiding Heuristic Planning[C]//Proceedings of the Eighteenth International Conference on International Conference on Automated Planning and Scheduling. Palo Alto: AAAI Press, 2008: 60-67.
16	Petrik M, Zilberstein S. Learning Heuristic Functions Through Approximate Linear Programming[C]//Proceedings of the Eighteenth International Conference on International Conference on Automated Planning and Scheduling. Palo Alto: AAAI Press, 2008: 248-255.
17	Blum A L, Furst M L. Fast Planning Through Planning Graph Analysis[J]. Artificial Intelligence, 1997, 90(1/2): 281-300.
18	Fox M, Long D. PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains[J]. Journal of Artificial Intelligence Research, 2003, 20: 61-124.
19	Edelkamp S, Hoffmann J. PDDL2.2: The Language for the Classical Part of the 4th International Planning Competition[R]. Technical Report 195, University of Freiburg, 2004.
20	Gerevini A, Long D. Preferences and Soft Constraints in PDDL3[C]//ICAPS Workshop on Planning with Preferences and Soft Constraints. United Kingdom: AAAI Press, 2006: 46-53
21	Höller Daniel, Behnke Gregor, Bercher Pascal, et al. HDDL: An Extension to PDDL for Expressing Hierarchical Planning Problems[C]//Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence and Thirty-Second Conference on Innovative Applications of Artificial Intelligence and Tenth Symposium on Educational Advances in Artificial Intelligence. Palo Alto: AAAI Press, 2020: 9883-9891.
22	Strobel Volker, Kirsch Alexandra. MyPDDL: Tools for Efficiently Creating PDDL Domains and Problems[M]//Vallati M, Kitchin D. Knowledge Engineering Tools and Techniques for AI Planning. Cham: Springer International Publishing, 2020: 67-90.
23	Tan Zhixuan. PDDL.jl: An Extensible Interpreter and Compiler Interface for Fast and Flexible AI Planning[D]. Cambridge: Massachusetts Institute of Technology, 2022.
24	Ana Margarida Amândio, José Manuel Coelho das Neves, Parente Manuel. Intelligent Planning of Road Pavement Rehabilitation Processes Through Optimization Systems[J]. Transportation Engineering, 2021, 5: 100081.
25	Hoffmann Jörg, Nebel Bernhard. The FF Planning System: Fast Plan Generation Through Heuristic Search[J]. Journal of Artificial Intelligence Research, 2001, 14(1): 253-302.
26	Gerevini Alfonso, Serina Ivan. LPG: A Planner Based on Local Search for Planning Graphs with Action Costs[C]//Proceedings of the Sixth International Conference on Artificial Intelligence Planning Systems. Palo Alto: AAAI Press, 2002: 13-22.
27	Georgievski Ilche, Aiello Marco. An Overview of Hierarchical Task Network Planning[EB/OL]. [2023-11-25]. .
28	Tate A, Drabble B, Kirby R. O-Plan2: An Open Architecture for Command, Planning and Control[J]. Intelligent Scheduling, 1994, 1: 213-239.
29	Hutchinson S A, Kak A C. Extending the Classical AI Planning Paradigm to Robotic Assembly Planning[C]//Proceedings of the IEEE International Conference on Robotics and Automation. Piscataway: IEEE, 1990: 182-189.
30	Nau D, Au T C, Ilghami O, et al. SHOP2: An HTN Planning System[J]. Journal of Artificial Intelligence Research, 2003, 20(1): 379-404.
31	Burch J R, Clarke E M, McMillan K L, et al. Symbolic Model Checking: 1020 States and Beyond[J]. Information and Computation, 1992, 98(2): 142-170.
32	Blum A L, Langford J C. Probabilistic Planning in the Graphplan Framework[C]//Recent Advances in AI Planning. Berlin: Springer Berlin Heidelberg, 2000: 319-332.
33	Smith D E, Weld D S. Conformant Graphplan[C]//Proceedings of the Fifteenth National/Tenth Conference on Artificial Intelligence/Innovative Applications of Artificial Intelligence. Palo Alto: AAAI Press, 1998: 889-896.
34	Weld D S, Anderson C R, Smith D E. Extending Graphplan to Handle Uncertainty and Sensing Actions[C]//Proceedings of the Fifteenth National/Tenth Conference on Artificial Intelligence/Innovative Applications of Artificial Intelligence. Palo Alto: AAAI Press, 1998: 897-904.
35	Russell S J, Norvig P. Artificial Intelligence: A Modern Approach[M]. London: Prentice Hall Press, 2010.
36	Weng Lilian. LLM Powered Autonomous Agents[EB/OL]. (2023-06-23) [2023-11-25]. .
37	Nwana H S, Ndumu D T. An Introduction to Agent Technology[M]//Nwana H S, Azarmi N. Software Agents and Soft Computing Towards Enhancing Machine Intelligence: Concepts and Applications. Berlin: Springer Berlin Heidelberg, 1997: 1-26.
38	Gravitas S. Auto-GPT[EB/OL]. (2023-04-01) [2023-11-25]. .
39	Mazzia Vittorio, Angarano Simone, Salvetti Francesco, et al. Action Transformer: A Self-attention Model for Short-time Pose-based Human Action Recognition[J]. Pattern Recognition, 2022, 124: 108487.
40	Zhou S, Xu F, Zhu H, et al. WebArena: A Realistic Web Environment for Building Autonomous Agents[C]//12th International Conference on Learning Representations, ICLR 2024. Hybrid, Vienna, Austria: International Conference on Learning Representations, ICLR, 2024:1-22.
41	Team XAgent. XAgent[EB/OL]. (2023-10-15) [2023-11-25]. .
42	Li Guohao, Hasan Abed Al Kader Hammoud, Itani Hani, et al. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society[C]//37th Conference on Neural Information Processing Systems (NeurIPS 2023). Red Hook: Curran Associates, Inc., 2023: 51991-52008.
43	Park J S, O'Brien J C, Cai C J, et al. Generative Agents: Interactive Simulacra of Human Behavior[C]//Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. New York: ACM, 2023: 1-22.
44	Qian Chen, Cong Xin, Yang Cheng, et al. Communicative Agents for Software Development[EB/OL]. (2023-07-16) [2023-11-25]. .
45	Wang Guanzhi, Xie Yuqi, Jiang Yunfan, et al. Voyager: An Open-ended Embodied Agent with Large Language Models[EB/OL]. (2023-10-19) [2023-11-25]. .
46	Gupta T, Kembhavi A. Visual Programming: Compositional Visual Reasoning Without Training[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2023: 14953-14962.
47	Surís Dídac, Menon S, Vondrick C. ViperGPT: Visual Inference via Python Execution for Reasoning[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE, 2023: 11854-11864.
48	Yang Zhengyuan, Li Linjie, Wang Jianfeng, et al. MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action[EB/OL]. (2023-03-20) [2023-11-25]. .
49	Valmeekam K, Marquez M, Sreedharan S, et al. On the Planning Abilities of Large Language Models: A Critical Investigation[C]//Proceedings of the 37th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 75993-76005.
50	Liu Bo, Jiang Yuqian, Zhang Xiaohan, et al. LLM+P: Empowering Large Language Models with Optimal Planning Proficiency[EB/OL]. (2023-09-27) [2023-11-25]. .
51	Dagan G, Keller F, Lascarides A. Dynamic Planning with a LLM[EB/OL]. (2023-08-11) [2023-11-25]. .
52	Zhang Hongxin, Du Weihua, Shan Jiaming, et al. Building Cooperative Embodied Agents Modularly with Large Language Models[EB/OL]. (2023-07-05) [2023-11-25]. .
53	Song C H, Sadler B M, Wu Jiaman, et al. LLM-planner: Few-shot Grounded Planning for Embodied Agents with Large Language Models[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE, 2023: 2986-2997.
54	Wei J, Wang Xuezhi, Schuurmans D, et al. Chain-of-thought Prompting Elicits Reasoning in Large Language Models[C]//Proceedings of the 36th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 24824-24837.
55	Kojima T, Gu Shixiang, Reid M, et al. Large Language Models are Zero-shot Reasoners[C]//Advances in Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2022: 22199-22213.
56	Wang Xuezhi, Wei J, Schuurmans D, et al. Self-consistency Improves Chain of Thought Reasoning in Language Models[EB/OL]. (2023-03-07) [2023-11-25]. .
57	Yao Shunyu, Yu Dian, Zhao J, et al. Tree of Thoughts: Deliberate Problem Solving with Large Language Models[C]//Proceedings of the 37th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 11809-11822.
58	Wang Yancheng, Jiang Ziyan, Chen Zheng, et al. RecMind: Large Language Model Powered Agent for Recommendation[C]//Findings of the Association for Computational Linguistics: NAACL 2024. Stroudsburg: ACL, 2024: 4351-4364.
59	Besta Maciej, Blach Nils, Kubicek Ales, et al. Graph of Thoughts: Solving Elaborate Problems with Large Language Models[C]//Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence. Reston, VA, USA: AIAA, 2024: 17682-17690.
60	Sel Bilgehan, Al-Tawaha Ahmad, Khattar Vanshaj, et al. Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models[C]//Proceedings of the 41st International Conference on Machine Learning. Chia Laguna Resort: PMLR, 2025: 44136-44189.
61	Zhang Yifan, Yang Jingqin, Yuan Yang, et al. Cumulative Reasoning with Large Language Models[EB/OL]. (2023-08-08) [2023-11-25]. .
62	Ding Ruomeng, Zhang Chaoyun, Wang Lu, et al. Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation[C]//Findings of the Association for Computational Linguistics: ACL 2024. Stroudsburg: ACL, 2024: 1638-1662.
63	Ning Xuefei, Lin Zinan, Zhou Zixuan, et al. Skeleton-of-thought: Prompting LLMs for Efficient Parallel Generation[EB/OL]. (2023-07-28) [2023-11-25]. .
64	Chen Wenhu, Ma Xueguang, Wang Xinyi, et al. Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks[EB/OL]. (2023-10-23) [2023-11-25]. .
65	Ye Yining, Cong Xin, Qin Yujia, et al. Large Language Model as Autonomous Decision Maker[EB/OL]. (2023-08-24) [2023-11-25]. .
66	Yao Shunyu, Zhao J, Yu Dian, et al. ReAct: Synergizing Reasoning and Acting in Language Models[EB/OL]. (2023-03-10) [2023-11-25]. .
67	Zhu Xizhou, Chen Yuntao, Tian Hao, et al. Ghost in the Minecraft: Generally Capable Agents for Open-world Environments via Large Language Models with Text-based Knowledge and Memory[EB/OL]. (2023-06-01) [2023-11-25]. .
68	Rana Krishan, Haviland Jesse, Garg Sourav, et al. SayPlan: Grounding Large Language Models Using 3D Scene Graphs for Scalable Robot Task Planning[EB/OL]. (2023-09-27) [2023-11-25]. .
69	Wang Zihao, Cai Shaofei, Chen Guanzhou, et al. Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-world Multi-task Agents[C]//Proceedings of the 37th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 34153-34189.
70	Huang Wenlong, Xia Fei, Xiao T, et al. Inner Monologue: Embodied Reasoning Through Planning with Language Models[C]//Proceedings of The 6th Conference on Robot Learning. Chia Laguna Resort: PMLR, 2023: 1769-1782.
71	Madaan A, Tandon N, Gupta P, et al. SELF-REFINE: Iterative Refinement with Self-feedback[C]//Proceedings of the 37th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2024: 46534-46594.
72	Miao Ning, Teh Y W, Rainforth T. SelfCheck: Using LLMs to Zero-shot Check Their Own Step-by-step Reasoning[EB/OL]. (2023-10-05) [2023-11-25]. .
73	Chen Polin, Chang Chengshang. InterAct: Exploring the Potentials of ChatGPT as a Cooperative Agent[EB/OL]. (2023-08-03) [2023-11-25]. .
74	Shinn N, Cassano F, Gopinath A, et al. Reflexion: Language Agents with Verbal Reinforcement Learning[C]//Advances in Neural Information Processing Systems. Red Hook: Curran Associates, Inc., 2023: 8634-8652.
75	LangChain. Introduction[EB/OL]. [2023-11-25]. .
76	Pandya Keivalya, Holia Mehfuza. Automating Customer Service Using LangChain: Building Custom Open-source GPT Chatbot for Organizations[EB/OL]. (2023-10-09) [2023-11-25]. .
77	Shen Yongliang, Song Kaitao, Tan Xu, et al. HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends in Hugging Face[EB/OL]. (2023-12-03) [2023-11-25]. .
78	Cai Yuzhe, Mao Shaoguang, Wu Wenshan, et al. Low-code LLM: Visual Programming over LLMs[EB/OL]. (2023-04-17) [2023-11-25]. .
79	Hong Sirui, Zheng Xiawu, Chen J, et al. MetaGPT: Meta Programming for Multi-agent Collaborative Framework[EB/OL]. (2023-08-01) [2023-11-25]. .
80	Zhou Wangchunshu, Jiang Yuchen, Li Long, et al. Agents: An Open-source Framework for Autonomous Language Agents[EB/OL]. [2023-11-25]. .
81	Anon. Prompt Flow[EB/OL]. (2023-06-30) [2023-12-27]. .
82	Beerbaum D O. Generative Artificial Intelligence (GAI) Ethics Taxonomy-applying ChatGPT for Robotic Process Automation(GAI-RPA)as Business Case[J]. Available at SSRN, 2023, 21(6):1-20.
83	Korzynski Paweł, Andrzej Krzysztof Kozminski, Baczynska Anna. Navigating Leadership Challenges with Technology: Uncovering the Potential of ChatGPT, Virtual Reality, Human Capital Management Systems, Robotic Process Automation, and Social Media[J]. International Entrepreneurship Review, 2023, 9(2): 7-18.
84	Ye Yining, Cong Xin, Tian Shizuo, et al. ProAgent: From Robotic Process Automation to Agentic Process Automation[EB/OL]. (2023-11-23) [2023-11-25]. .
85	Radford A, Kim J W, Hallacy C, et al. Learning Transferable Visual Models from Natural Language Supervision[C]//Proceedings of the 38th International Conference on Machine Learning. Chia Laguna Resort: PMLR, 2021: 8748-8763.
86	Li Junnan, Li Dongxu, Xiong Caiming, et al. BLIP: Bootstrapping Language-image Pre-training for Unified Vision-language Understanding and Generation[C]//Proceedings of the 39th International Conference on Machine Learning. Chia Laguna Resort: PMLR, 2022: 12888-12900.
87	Gabriel S, Celikyilmaz A, Jha R, et al. GO FIGURE: A Meta Evaluation of Factuality in Summarization[C]//Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Stroudsburg: ACL, 2021: 478-487.
88	Gou Zhibin, Shao Zhihong, Gong Yeyun, et al. CRITIC: Large Language Models Can Self-correct with Tool-interactive Critiquing[EB/OL]. (2023-05-19) [2023-11-25]. .
89	Fu Bang. GPTCache: An Open-source Semantic Cache for LLM Applications Enabling Faster Answers and Cost Savings[C]//Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023). Stroudsburg: ACL, 2023: 212-218.
90	Feng Xidong, Wan Ziyu, Wen Muning, et al. Alphazero-like Tree-search Can Guide Large Language Model Decoding and Training[EB/OL]. (2023-09-29) [2023-11-25]. .
91	Fedus W, Zoph B, Shazeer N. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity[J]. The Journal of Machine Learning Research, 2022, 23(1): 5232-5270.
92	Schick Timo, Dwivedi-Yu Jane, Dessì Roberto, et al. Toolformer: Language Models Can Teach Themselves to Use Tools[EB/OL]. [2023-11-25]. .
93	Liu Minghuan, Zhu Menghui, Zhang Weinan. Goal-conditioned Reinforcement Learning: Problems and Solutions[EB/OL]. (2022-09-02) [2023-11-25]. .
94	Gao Luyu, Madaan A, Zhou Shuyan, et al. PAL: Program-aided Language Models[C]//Proceedings of the 40th International Conference on Machine Learning. Chia Laguna Resort: PMLR, 2023: 10764-10799.
95	Wang Xingyao, Li Sha, Ji Heng. Code4Struct: Code Generation for Few-shot Event Structure Prediction[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2023: 3640-3663.
96	Chen A, Scheurer Jérémy, Korbak T, et al. Improving Code Generation by Training with Natural Language Feedback[EB/OL]. (2023-03-28) [2023-11-25]. .
97	Palantir Technologies Inc. AIP[EB/OL]. (2023-09-01) [2023-12-25]. .
98	Su Yihao. Artificial Intelligence: The Significance of Tesla Bot[J]. Highlights in Science, Engineering and Technology, 2023, 39: 1351-1355.
99	Huang W, Wang C, Zhang R, et al. VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models[C]//7th Annual Conference on Robot Learning. Atlanta, USA: PMLR, 2023, 229: 540-562.

[1]	Wang Rui, Li Xiangyang, Wang Dong, Ma Hongguang, Zhang Zhili. A Radar Countermeasure Modeling Method Incorporating Cognitive Bias [J]. Journal of System Simulation, 2025, 37(4): 1090-1101.
[2]	Wang Yushuai, Si Guangya. Capability Dependency Analysis Based on Kill Chain and FDNA [J]. Journal of System Simulation, 2025, 37(4): 1076-1089.
[3]	Huang Jie, Huang Jie. An Intelligent Tracking Control Method for Unmanned Vehicles with Time-varying Disturbances [J]. Journal of System Simulation, 2025, 37(4): 1063-1075.
[4]	Xu Ming, Li Jinye, Zuo Dongyu, Zhang Jing. Signal Timing Optimization via Reinforcement Learning with Traffic Flow Prediction [J]. Journal of System Simulation, 2025, 37(4): 1051-1062.
[5]	Li Jie, Liu Yang, Li Liang, Su Bengan, Wei Jialong, Zhou Guangda, Shi Yanmin, Zhao Zhen. Remote Sensing Small Object Detection Based on Cross-stage Two-branch Feature Aggregation [J]. Journal of System Simulation, 2025, 37(4): 1025-1040.
[6]	Zhang Xingyu, Wu Baolei, Wang Jun, Hong Miaoying, Wang Jiahui, Qi Yongqiang. Research on Dual-layer Path Planning Method for Lunar Rover Based on Slip Prediction [J]. Journal of System Simulation, 2025, 37(4): 1008-1024.
[7]	Wan Shizheng, Cheng Yu, Zhang Xu, Fan Xuwei. Enhancement of Hardware-in-loop Simulation Ability for Homing Guidance Through Adaptive Field-of-view Method [J]. Journal of System Simulation, 2025, 37(3): 563-570.
[8]	Guo Bo, Tie Ming, Fan Wenhui. Vibration Simulation and Multivariate Statistical Analysis Method of Composite Structures [J]. Journal of System Simulation, 2025, 37(3): 571-583.
[9]	Zhang Lei, Zhang Xuechao, Wang Chao, Bo Xianglei. An Intelligent Ambulance Regulation Model Based on Online Reinforcement Learning Algorithm [J]. Journal of System Simulation, 2025, 37(3): 584-594.
[10]	Li Zhaobin, Ye Jun, Zhou Haoyan, Wang Yixin, Han Yuzhen. Three-way Decision Clustering Algorithm Fusion of Mutant Fireflies Algorithm [J]. Journal of System Simulation, 2025, 37(3): 646-656.
[11]	Xu Ming, Qi Guangyao, Qi Geqi. Fine-grained Traffic Flow Inference Model Based on Dynamic Back Projection Network [J]. Journal of System Simulation, 2025, 37(3): 657-666.
[12]	Lin Guijuan, Li Zihan, Wang Yu. Research on Improved A* Algorithm Path Planning Based on Global Key Point Extraction [J]. Journal of System Simulation, 2025, 37(3): 667-678.
[13]	Li Ruoqing, Zhao Yaochi, Hu Zhuhua, Qi Wenlu, Liu Guangfeng. TOHF: A Feature Extractor for Resource-constrained Indoor VSLAM [J]. Journal of System Simulation, 2025, 37(3): 691-703.
[14]	Cao Xi, Liu Bo, Su Bingzhi, Nie Tao. Design and Verification of Display and Control System Based on MBSE and VAPS for Civil Helicopter [J]. Journal of System Simulation, 2025, 37(3): 704-717.
[15]	Chen Xue, Cao Jianwen. CAE Simulation Optimization Method Based on Dynamic Coupling Model [J]. Journal of System Simulation, 2025, 37(3): 718-731.