AdaPlanner: Adaptive Planning from Feedback with Language Models
Open accessAbstract
Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans that are not adaptable to environmental feedback. Consequently, the sequential decision-making performance of LLM agents degenerates with problem complexity and plan horizons increase. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback. In AdaPlanner, the LLM agent adaptively refines its plan from feedback with both in-plan and out-of-plan refinement strategies. To mitigate hallucination, we develop a code-style LLM prompt structure that facilitates plan generation across a variety of tasks, environments, and agent capabilities. Furthermore, we propose a skill discovery mechanism that leverages successful plans as few-shot exemplars, enabling the agent to plan and refine with fewer task demonstrations. Our experiments in the ALFWorld and MiniWoB++ environments demonstrate that AdaPlanner outperforms state-of-the-art baselines by 3.73% and 4.11% while utilizing 2x and 600x fewer samples, respectively.
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?
The adaptive closed-loop framework of AdaPlanner eliminates the need for prior knowledge about feedback structures and enables more efficient decision-making.
“This adaptive closed-loop framework eliminates the need for prior knowledge about feedback structures and enables more efficient decision-making.”
From A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence (2025) · cites this paper as Sun et al., 2023
The Open-Loop Methods passage says AdaPlanner's adaptive closed-loop framework alleviates the need for prior knowledge about feedback structure and leads to more efficient decision-making. It does not say the need is eliminated, so the claim overstates that part. (LLM, conf=0.86)
Experimental — accuracy not yet measuredAdaPlanner enables closed-loop adaptive planning by allowing LLM agents to revise their plans based on both in-plan and out-of-plan feedback, while also mitigating hallucination via code-style prompts and leveraging skill discovery.
“AdaPlanner enables closed-loop adaptive planning by allowing LLM agents to revise their plans based on both in-plan and out-of-plan feedback, while also mitigating hallucination via code-style prompts and leveraging skill discovery.”
From A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence (2025) · cites this paper as Sun et al., 2023
Some agents evolve online not by updating their model weights, but by refining their plans and skill libraries on the fly.
“Some agents evolve online not by updating their model weights, but by refining their plans and skill libraries on the fly.”
From A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence (2025) · cites this paper as Sun et al., 2023
AdaPlanner adapts its plan within a task by generating an initial plan, receiving feedback from the environment, and refining the plan online.
“AdaPlanner(Sun et al., 2023) focuses on adapting its plan within a task; it generates an initial plan, receives feedback from the environment, and refines the plan online.”
From A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence (2025) · cites this paper as Sun et al., 2023
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
No references could be resolved yet.
Research works printed but not linked: 22
- T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901, 2020.
- W. Chen, X. Ma, X. Wang, and W. W. Cohen. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv, page 2211.12588v3, 2022.
- L. Gao, A. Madaan, S. Zhou, U. Alon, P. Liu, Y. Yang, J. Callan, and G. Neubig. Pal: Program- aided language models. arXiv, page 2211.10435v2, 2022.
- I. Gur, O. Nachum, Y. Miao, M. Safdari, A. Huang, A. Chowdhery, S. Narang, N. Fiedel, and A. Faust. Understanding html with large language models. arXiv, page 2210.03945v1, 2022.
- W. Huang, P. Abbeel, D. Pathak, and I. Mordatch. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. arXiv, page 2201.07207v2, 2022.
- W. Huang, F. Xia, T. Xiao, H. Chan, J. Liang, P. Florence, A. Zeng, J. Tompson, I. Mordatch, Y. Chebotar, P. Sermanet, N. Brown, T. Jackson, L. Luu, S. Levine, K. Hausman, and B. Ichter. Inner monologue: Embodied reasoning through planning with language models. arXiv, page 2207.05608v1, 2022.
- P. C. Humphreys, D. Raposo, T. Pohlen, G. Thornton, R. Chhaparia, A. Muldal, J. Abramson, P. Georgiev, A. Goldin, A. Santoro, and T. Lillicrap. A data-driven approach for learning to control computers. arXivProceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022, page 2202.08137v2, 2022.
- G. Kim, P. Baldi, and S. McAleer. Language models can solve computer tasks. arXiv, page 2303.17491v1, 2023.
- J. Liang, W. Huang, F. Xia, P. Xu, K. Hausman, B. Ichter, P. Florence, and A. Zeng. Code as policies: Language model programs for embodied control. arXiv, page 2209.07753v3, 2022.
- E. Z. Liu, K. Guu, P. Pasupat, and P. Liang. Reinforcement learning on web interfaces using workflow-guided exploration. In International Conference on Learning Representations, 2018.
- P. Lu, B. Peng, H. Cheng, M. Galley, K.-W. Chang, Y. N. Wu, S.-C. Zhu, and J. Gao. Chameleon: Plug-and-play compositional reasoning with large language models. arXiv preprint arXiv:2304.09842, 2023. · arXiv
- L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, et al. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730-27744, 2022.
- A. Parisi, Y. Zhao, and N. Fiedel. Talm: Tool augmented language models. arXiv preprint arXiv:2205.12255, 2022. · arXiv
- T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, L. Zettlemoyer, N. Cancedda, and T. Scialom. Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761, 2023. · arXiv
- Y. Shen, K. Song, X. Tan, D. Li, W. Lu, and Y. Zhuang. Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580, 2023. · arXiv
- N. Shinn, B. Labash, and A. Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366, 2023. · arXiv
- M. Shridhar, X. Yuan, M.-A. Cote, Y. Bisk, A. Trischler, and M. Hausknecht. {ALFW}orld: Aligning text and embodied environments for interactive learning. In International Conference on Learning Representations, 2021.
- I. Singh, V. Blukis, A. Mousavian, A. Goyal, D. Xu, J. Tremblay, D. Fox, J. Thomason, and A. Garg. Progprompt: Generating situated robot task plans using large language models. In Second Workshop on Language and Reinforcement Learning, 2022.
- Z. Wang, S. Cai, A. Liu, X. Ma, and Y. Liang. Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. arXiv, page 2302.01560v1, 2023.
- J. Wei, X. Wang, D. Schuurmans, M. Bosma, B. Ichter, F. Xia, E. Chi, Q. Le, and D. Zhou. Chain- of-thought prompting elicits reasoning in large language models. arXiv, page 2201.11903v6, 2022.
- S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. R. Narasimhan, and Y. Cao. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, 2023.
- D. Zhou, N. Schärli, L. Hou, J. Wei, N. Scales, X. Wang, D. Schuurmans, C. Cui, O. Bousquet, Q. Le, and E. Chi. Least-to-most prompting enables complex reasoning in large language models. arXiv, page 2205.10625v2, 2022.
Cited by
Sorted by citations
Expel: LLM agents are experiential learners
Zhao, A., Huang, D., Xu, Q., Lin, M., Liu, Y.-J., & Huang, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29936 · Cited by 153 · see citing works
PlanGenLLMs: A Modern Survey of LLM Planning Capabilities
Wei, H., Zhang, Z., He, S., Xia, T., Pan, S., & Liu, F. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.958 · Cited by 36 · see citing works
<b>JARVIS</b> -1: Open-World Multi-Task Agents With Memory-Augmented Multimodal Language Models
Wang, Z., Cai, S., Liu, A., Jin, Y., Hou, J., Zhang, B., Lin, H., He, Z., Zheng, Z., Yang, Y., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3511593 · Cited by 36 · see citing works
Wang, Z. Z., Mao, J., Fried, D., & Neubig, G. (2024) · arXiv · doi:10.48550/arxiv.2409.07429 · Cited by 5 · see citing works
A knowledge-driven framework for Robotic Odor Source Localization using large language models
Mahmud, K. R., Wang, L., Hassan, S., & Zhang, Z. (2025) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2025.104915 · Cited by 10 · see citing works
Gao, H.-A., Geng, J., Hua, W., Hu, M., Juan, X., Liu, H., Liu, S., Qiu, J., Qi, X., Wu, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2507.21046 · Cited by 3 · see citing works
Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
Potamitis, N., & Arora, A. (2025) · arXiv · doi:10.48550/arxiv.2504.12951
iCLP: Large Language Model Reasoning with Implicit Cognition Latent Planning
Chen, S., & Niu, D. (2025) · arXiv · doi:10.48550/arxiv.2512.24014
- Authors
- Sun, H., Zhuang, Y., Kong, L., Dai, B., & Zhang, C.
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 58202-58245
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133187879
- Cited by
- 31
- References
- 0
- Citations by year
- 2026: 12 · 2025: 5 · 2024: 10 · 2023: 4
- FWCI
- 5.50
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- 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 › Artificial Intelligence Applications
- Keywords
- adaptive planning, language models, large language models
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
