We are pleased to announce the 2nd Workshop on Compositional Learning: Safety, Interpretability, and Agents, to be held in conjunction with ICML 2026 at the COEX Convention & Exhibition Center, July 2026.
We invite submissions of original research that explores the theoretical foundations of compositionality and its role in the era of foundation models and agents.
More information at https://compositional-learning.github.io.

Workshop Overview
Compositionality, defined as the ability to construct and reason about complex concepts from reusable components, is a hallmark of human cognition and the key to robust generalization. Despite the astonishing progress of modern AI systems, it remains an open question whether they truly capture and leverage the compositional nature of many real-world domains. The workshop explores this pressing challenge across multiple critical dimensions. We welcome contributions focusing on the theoretical foundations of compositionality, its central role in the age of foundation models and agents, and its impact on achieving robustness and systematic out-of-domain generalization.

Topics of Interest
We encourage submissions on (but not limited to):
- Compositionality in Action: Agentic AI, Planning, and Tool Use
- Safety: architectures and representations for robust and generalizable systems
- Explainability: representations and reasoning in foundation models
- Theoretical foundations and general principles of compositionality in AI
- Multimodal compositionality
- Modular and dynamic architectures
- Continual/transfer learning through compositionality
- Compositional learning for various application domains, such as computer vision, natural language processing, -reinforcement learning, and science

Submission Guidelines
- Submission Format: 4-page or 8-page papers (excluding references and appendix). Max file size: 20MB.
- Style: All submissions must be formatted using the ICML 2026 LaTeX style file.
- Review Process: Double-blind peer review. Submissions must be anonymized PDFs.
- Dual-Submission Policy: We welcome ongoing/unpublished work, papers currently under review, or recently accepted work without published proceedings.
- Submission System: Papers must be submitted via the OpenReview Portal at https://openreview.net/group?id=ICML.cc/2026/Workshop/CompLearn.
- Archival Status: The workshop will be non-archival and will not have official proceedings.

Important Dates
- Paper submissions open: 30th March 2026 AOE
- Paper submission deadline: 24th April 2026 AOE
- Notification to authors: 15th May 2026 AOE
- Workshop date: 10th or 11th July 2026 AOE

Contact
For questions, please contact the workshop organizers at: compositional-learning-icml-2026@googlegroups.com
We are also recruiting reviewers. If you would like to become a reviewer for this workshop, please let us know here: https://forms.gle/nG4idePAF4Qp6TNk8.