Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
Open accessThe DOI matches its OpenAlex record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Large language models (LLMs) have achieved remarkable progress in solving various natural language processing tasks due to emergent reasoning abilities. However, LLMs have inherent limitations as they are incapable of accessing up-to-date information (stored on the Web or in task-specific knowledge bases), using external tools, and performing precise mathematical and logical reasoning. In this paper, we present Chameleon, an AI system that mitigates these limitations by augmenting LLMs with plug-and-play modules for compositional reasoning. Chameleon synthesizes programs by composing various tools (e.g., LLMs, off-the-shelf vision models, web search engines, Python functions, and heuristic-based modules) for accomplishing complex reasoning tasks. At the heart of Chameleon is an LLM-based planner that assembles a sequence of tools to execute to generate the final response. We showcase the effectiveness of Chameleon on two multi-modal knowledge-intensive reasoning tasks: ScienceQA and TabMWP. Chameleon, powered by GPT-4, achieves an 86.54% overall accuracy on ScienceQA, improving the best published few-shot result by 11.37%. On TabMWP, GPT-4-powered Chameleon improves the accuracy by 17.0%, lifting the state of the art to 98.78%. Our analysis also shows that the GPT-4-powered planner exhibits more consistent and rational tool selection via inferring potential constraints from instructions, compared to a ChatGPT-powered planner. The project is available at https://chameleon-llm.github.io.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Large Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013
VisualBERT: A Simple and Performant Baseline for Vision and Language
Li, L. H., Yatskar, M., Yin, D., Hsieh, C.-J., & Chang, K.-W. (2019) · arXiv · doi:10.48550/arxiv.1908.03557 · Cited by 1,198
Self-citationToolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150
Simple statistical gradient-following algorithms for connectionist reinforcement learning
Williams, R. J. (1992) · Machine Learning · doi:10.1023/a:1022672621406 · Cited by 817
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
Shen, Y., Song, K., Tan, X., Li, D., Lu, W., & Zhuang, Y. (2023) · arXiv · doi:10.48550/arxiv.2303.17580 · Cited by 477
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
Shen, Y., Song, K., Tan, X., Li, D., Lu, W., & Zhuang, Y. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1657 · Cited by 475
ViperGPT: Visual Inference via Python Execution for Reasoning
Surís, D., Menon, S., & Vondrick, C. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01092 · Cited by 273
Explainable Neural Computation via Stack Neural Module Networks
Hu, R., Andreas, J., Darrell, T., & Saenko, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_4 · Cited by 216
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., & Duan, N. (2023) · arXiv · doi:10.48550/arxiv.2303.04671 · Cited by 197
Cited by
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972
The rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
A survey on multimodal large language models
Yin, S., Fu, C., Zhao, S., Li, K., Sun, X., Xu, T., & Chen, E. (2024) · National Science Review · doi:10.1093/nsr/nwae403 · Cited by 893
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
Tang, X., Zou, A., Zhang, Z., Li, Z., Zhao, Y., Zhang, X., Cohan, A., & Gerstein, M. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.33 · Cited by 376
A Survey on Multimodal Large Language Models for Autonomous Driving
Cui, C., Ma, Y., Cao, X., Ye, W., Zhou, Y., Liang, K., Chen, J., Lu, J., Yang, Z., Liao, K.-D., et al. (2024) · 2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00106 · Cited by 369
Foundation Models Defining a New Era in Vision: A Survey and Outlook
Awais, M., Naseer, M., Khan, S., Anwer, R. M., Cholakkal, H., Shah, M., Yang, M.-H., & Khan, F. S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3506283 · Cited by 304
Kapoor, R., Butala, Y. P., Russak, M., Koh, J. Y., Kamble, K., Alshikh, W., & Salakhutdinov, R. (2024) · arXiv · doi:10.48550/arxiv.2402.17553 · Cited by 93
Optimizing generative AI by backpropagating language model feedback
Yuksekgonul, M., Bianchi, F., Boen, J., Liu, S., Lu, P., Huang, Z., Guestrin, C., & Zou, J. (2025) · Nature · doi:10.1038/s41586-025-08661-4 · Cited by 85
Self-citationV*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
Wu, P., & Xie, S. (2023) · arXiv · doi:10.48550/arxiv.2312.14135 · Cited by 74
V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
Wu, P., & Xie, S. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01243 · Cited by 74
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
Chen, Z., Zhou, K., Zhang, B., Gong, Z., Zhao, X., & Wen, J.-R. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.985 · Cited by 30
CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models
Qian, C., Han, C., Fung, Y., Qin, Y., Liu, Z., & Ji, H. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.462 · Cited by 24
Defeating Prompt Injections by Design
Debenedetti, E., Shumailov, I., Fan, T., Hayes, J., Carlini, N., Fabian, D., Kern, C., Shi, C., Terzis, A., & Tramèr, F. (2026) · 2026 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml68715.2026.00040 · Cited by 15
Kapoor, R., Butala, Y. P., Russak, M., Koh, J. Y., Kamble, K., AlShikh, W., & Salakhutdinov, R. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-73113-6_10 · Cited by 12
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
Suzgun, M., Yuksekgonul, M., Bianchi, F., Jurafsky, D., & Zou, J. (2025) · arXiv · doi:10.48550/arxiv.2504.07952
Can an LLM Induce a Graph? Investigating Memory Drift and Context Length
Yousuf, R. B., Khatri, A., Xu, S., Sharma, M., & Ramakrishnan, N. (2025) · 2025 IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg66886.2025.00056
InferCept: Efficient Intercept Support for Augmented Large Language Model Inference
Abhyankar, R., He, Z., Srivatsa, V., Zhang, H., & Zhang, Y. (2024) · arXiv · doi:10.48550/arxiv.2402.01869
Metadata
- Authors
- Lu, P., Peng, B., Cheng, H., Galley, M., Chang, K.-W., Wu, Y. N., Zhu, S. C., & Gao, J.
- Venue
- neural information processing systems
- Published
- 2023-01-01
- Pages
- 43447-43478
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133217858
- Cited by
- 120
- References
- 14
- FWCI
- 22.68
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.