Call for Papers

Important Dates

• Submission Deadline: September 10, 2026
• Review Period: September 11–25, 2026
• Decisions: September 29, 2026

Guidelines

• Paper submission is hosted on OpenReview.
• We welcome short papers up to 4 pages or long papers up to 8 pages, not including references or appendix.
  • The paper should be anonymized and uploaded to OpenReview as a single PDF.
  • You may use as many pages of references and appendix as you wish, but reviewers are not required to read the appendix.
  • Posting papers on preprint servers like ArXiv is permitted.
• This is a non-archival workshop. No submission will be indexed nor have archival proceedings.
  • Accepted papers will appear on the workshop website. They will also be available on OpenReview and the NeurIPS virtual site.
  • We accept submissions that are under review at other venues (e.g., ICLR 2027), as long as this does not violate the dual-submission / anonymity policy of the other venue.
• The review process will be double-blind.
  

Topics of Interest

Recent progress in foundation models has pushed context windows to 128K, 1M tokens, and beyond. Yet the next challenge is not only making context longer, but enabling models to use it effectively in long-horizon agentic frameworks. What are the key challenges in building reliable long-context agents? How can models manage growing reasoning traces and feedbacks from environment? How can long context improve planning, memory, tool use, multimodal interaction, and sustained reasoning in demanding domains such as AI for scientific discovery? We welcome works that address these challenges, foster discussion, developments, and evaluation of long-context foundation models across disciplines, including but not limited to:

• Long-context and long-horizon agentic foundation models
• Novel modeling and training approaches
• Efficiency techniques for foundation models
• Robust evaluation
• Long-context reasoning
• Long-context multi-modal learning
• Long-horizon AI for science

Speakers

Yu Sun
Stanford University
Nvidia

Dan Fu
University of California, San Diego
Together AI

Kristen Grauman
University of Texas at Austin

More to be announced.

Panelists

Jiayuan Mao
University of Pennsylvania

More to be announced.

Organizers

Zexue He
Stanford University

Howard Yen
Princeton University

Amanda Bertsch
Carnegie Mellon University

Seungju Han
Stanford University

Alex "Sandy" Pentland
MIT
Stanford University

Danqi Chen
Princeton University

Yejin Choi
Stanford University