PlanGenLLMs: A Modern Survey of LLM Planning Capabilities
Open accessAbstract
LLMs have immense potential for generating plans, transforming an initial world state into a desired goal state.A large body of research has explored the use of LLMs for various planning tasks, from web navigation to travel planning and database querying.However, many of these systems are tailored to specific problems, making it challenging to compare them or determine the best approach for new tasks.There is also a lack of clear and consistent evaluation criteria.Our survey aims to offer a comprehensive overview of current LLM planners to fill this gap.It builds on foundational work by Kartam and Wilkins (1990) and examines six key performance criteria: completeness, executability, optimality, representation, generalization, and efficiency.For each, we provide a thorough analysis of representative works and highlight their strengths and weaknesses.Our paper also identifies crucial future directions, making it a valuable resource for both practitioners and newcomers interested in leveraging LLM planning to support agentic workflows.1
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Generative systems' design lacks intrinsic feedback loops, state management, or multi-step planning, which are requirements for autonomous decision-making and iterative goal refinement.
“Their design also lacks intrinsic feedback loops [110], state management [111,112], or multi-step planning a requirement for autonomous decision-making and iterative goal refinement [113, 114].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [114]
The Introduction (page unavailable) says LLMs struggle with independent planning and that closed-loop planning uses feedback to handle complex, long-horizon environments. This supports a limitation in unaided planning, but not the categorical claim that generative systems lack multi-step planning or that it is a stated requirement for autonomous decision-making and iterative goal refinement. The adjacent claims about feedback loops and state management have separate citations in the citing sentence. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 15
- Faeze Brahman, Chandra Bhagavatula, Valentina Py- atkin, Jena D Hwang, Xiang Lorraine Li, Hi- rona Jacqueline Arai, Soumya Sanyal, Keisuke Sak- aguchi, Xiang Ren, and Yejin Choi. 2024. Plasma: Procedural knowledge models for language-based planning and re-planning. In The Twelfth Interna- tional Conference on Learning Representations.
- Zhenfang Chen, Delin Chen, Wenjun Sun, Rui abd Liu, and Chuang Gan. 2025. Autonomous agents from au- tomatic reward modeling and planning. In The Thir- teenth International Conference on Learning Repre- sentations.
- Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2024. Mind2web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems, 36.
- Alfonso Gerevini, Ivan Serina, et al. 2002. Lpg: A planner based on local search for planning graphs with action costs. In Aips, volume 2, pages 281-290.
- Shiguang Guo, Ziliang Deng, Hongyu Lin, Yaojie Lu, Xianpei Han, and Le Sun. 2024. Open grounded planning: Challenges and benchmark construction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, Au- gust 11-16, 2024, pages 4982-5003. Association for Computational Linguistics. · DOI
- Hanxu Hu, Hongyuan Lu, Huajian Zhang, Yun-Ze Song, Wai Lam, and Yue Zhang. 2024. Chain-of-symbol prompting for spatial reasoning in large language models. In First Conference on Language Modeling.
- Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022a. Language models as zero- shot planners: Extracting actionable knowledge for embodied agents. In International conference on machine learning, pages 9118-9147. PMLR.
- Kurt Konolige and Nils J Nilsson. 1980. Multiple-agent planning systems. In AAAI, volume 80, pages 138- 142.
- Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, et al. 2024e. Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls. Advances in Neural Information Processing Systems, 36.
- Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clin- ton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Akyürek, Anima Anandkumar, et al. 2022. Pre- trained language models for interactive decision- making. Advances in Neural Information Processing Systems, 35:31199-31212.
- Nir Lipovetzky, Miquel Ramirez, Christian Muise, and Hector Geffner. 2014. Width and inference based planners: Siw, bfs (f), and probe. Proceedings of the 8th International Planning Competition (IPC-2014), page 43.
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9.
- Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the lim- its of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1-67.
- Shreyas Sundara Raman, Vanya Cohen, Eric Rosen, Ifrah Idrees, David Paulius, and Stefanie Tellex. 2022. Planning with large language models via corrective re-prompting. In NeurIPS 2022 Foundation Models for Decision Making Workshop.
- Xixi Wu, Yifei Shen, Caihua Shan, Kaitao Song, Siwei Wang, Bohang Zhang, Jiarui Feng, Hong Cheng, Wei Chen, Yun Xiong, et al. 2024. Can graph learning improve planning in llm-based agents? In The Thirty- eighth Annual Conference on Neural Information Processing Systems.
Cited by
Sorted by citations
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 244 · see citing works
LLMs and IoT: A Comprehensive Survey on Large Language Models and the Internet of Things
Sarhaddi, F., Nguyen, N. T., Zuniga, A., Khan, M., Hui, P., Tarkoma, S., Flores, H., & Nurmi, P. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3680064 · Cited by 21 · see citing works
Medea: An AI agent for therapeutic reasoning across biological contextsPreprint
Sui, P., Li, M. M., Munson, B. P., Gao, S., Shen, W., Giunchiglia, V., Shen, A. N., Huang, Y., Kong, Z., Licon, K., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.01.16.696667 · Cited by 11 · see citing works
A survey of foundation models for IoT: taxonomy and criteria-based analysis
Wei, H., Lee, D. Y., Rohal, S., Hu, Z., Rossi, R. A., Fang, S., & Pan, S. (2025) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-025-00208-w · Cited by 8 · see citing works
Self-citationAhmadpanah, S. H. (2025) · Computing · doi:10.1007/s00607-025-01609-6 · Cited by 5 · see citing works
Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures
Wang, Z., Gong, M.-C., Sun, Q., Xu, J., Mao, S., Jin, X., Han, Q.-L., & Tang, Y. (2026) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2026.126113 · Cited by 2 · see citing works
LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation
Xia, C., Peng, Y., & Wang, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-0363-5_28 · Cited by 2 · see citing works
Verifiable Reasoning for LLM-based Generative Recommendation
Lin, X., Zeng, H., Yu, H., Xia, Y., Zhang, J. J., Singh, A., Liu, F., Wang, W., Feng, F., Chua, T., et al. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809622 · Cited by 2 · see citing works
Self-citationSEAL: Self-evolving agentic learning for conversational question answering over knowledge graphs
Wang, H., Zhong, J., Wang, C., Nie, Z., Li, Z., Yao, S., Li, Y., & Li, X. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133998
SagaLLM: Persistent Context Management, Constraint Validation, and Transaction Guarantees
Chang, E. Y. (2025) · ACM eBooks · doi:10.1145/3749421.3749435
Symbolic wrappers enable precise human in the loop operation for large action models
Sangchai, K., Boonpun, M., Kraipetchara, W., & Garcia, P. (2026) · Discover Robotics · doi:10.1007/s44430-026-00023-7
From Struggle to Success: Context-Aware Guidance for Screen Reader Users in Computer Use
Chen, N., Lu, J., Wang, Z., Qiu, L. K., Chen, S., & Yang, Y. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790661
Graph Minds: Exploring Social Structures Through LLM-Based Community Detection
Gujral, E., & Sinha, A. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-16719-4_1
Integrating Large Language Models for Explainable Human-Machine Teaming in Autonomous Vehicles
Perez, J. P., Romero, A., Infante, W., Malafiej, B., & Bellas, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-27317-8_17
RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution
Srivastava, A., Khojastepour, M. A. A., Coviello, G., Rao, K., Chakradhar, S., & Ulukuş, Ş. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536499
InScribe: Intelligent Augmentation of Natural-Language Statements with Data Facts
Chen, C., Liu, Y., Shi, D., Cao, S., & Cao, N. (2026) · IEEE Pacific Visualization Conference (PacificVis) · doi:10.1109/pacificvis68791.2026.00021
LLM-FDC: LLM-Driven Fuzzy Rule Generation and Confidence-Based Decision-Making
Han, S., Hu, T., & Ma, H. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-1635-2_24
Zhang, J., Jiang, J., Zhang, C., Mo, F., Li, L., & Zeng, D. (2026) · IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi69914.2026.11685853
Answer First, Evidence Second? Uncovering Hidden Risks in Well-Structured AI Search Summaries
Li, J., Chen, X., Xu, R., Lin, H., Lu, Y., Fan, Z., Han, X., & Sun, L. (2026) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3805712.3809913
Agents in the Wild: Where Research Meets Deployment
Yang, G. H., Venkit, P. N., Sedghamiz, H., Santus, E., Dibia, V. C., & Baldini, I. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3816449
Machine Common Sense: A Grand Challenge in Artificial Intelligence
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789272
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789276
Commonsense Knowledge versus Reasoning
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789275
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789277
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789274
(2026) · ACM eBooks · doi:10.1145/3789270.3789271
Multi-disciplinary Perspectives on Defining Common Sense
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789273
(2026) · ACM eBooks · doi:10.1145/3789270.3844419
Common Sense in Large Language Models
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789279
(2026) · ACM eBooks · doi:10.1145/3789270.3844418
Kejriwal, M. (2026) · ACM eBooks · doi:10.1145/3789270.3789278
Research and Development of an Intelligent Assistant for Planning a Lean IT Startup
Parkhomenko, I., Khomenko, A., Parkhomenko, A., Dubrovin, V. I., Parkhomenko, A., & Wolff, C. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11700164
Task-Tree A-Star: A Hierarchical Framework for Long-Horizon Task Planning with Large Language Models
Li, Z., Zhang, Z., Lu, Y., & Li, G. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729884
Self-citationLLM-based agents for generalized web automation and schema-guided data extraction: a survey
Khayoub, I., Chadi, M.-A., Mousannif, H., & Mohamed, F. A. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01335-y
- Authors
- Wei, H., Zhang, Z., He, S., Xia, T., Pan, S., & Liu, F.
- Affiliations
- University of California, Merced (US)
- Emory University (US)
- Venue
- Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2025
- Pages
- 19497-19521
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4412944859
- Cited by
- 36
- References
- 0
- Citations by year
- 2026: 32 · 2025: 4
- FWCI
- 34.32
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (2303655, CAREER)
- U.S. Department of Commerce
- University of California Merced
- Economic Development Administration
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- large language models, LLM-based planning, plan generation, completeness, executability, optimality, representation, generalization, efficiency, agentic workflows, web navigation, tourism planning, database queries
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
