We are inviting submissions of short papers (maximum 8 pages) outlining new research, with a deadline of January 31, 2026. We welcome papers on any of the following topics, or anything else where the authors convincingly argue that it advances the field of AI safety.

• Interpretability and Explainability

• Safety Evaluations for Frontier AI

• (Scalable) Oversight and Control

• Alignment

• Robustness and Reliability

• Agent Foundations

• Frontier Safety and Governance

• Multi-agent Safety

• Safety by Design

• AI Cybersecurity

• Long-Term and Societal Risk Modeling

We encourage you to consider submitting to TAIS 2026 even if you think your work might not be relevant; irrelevant submissions are not a substantial burden on our editorial team, and our editors like reading oblique and hard-to-categorize research.

We also welcome position pieces bringing clarification to complex topics (especially topics not prominent in the AI Safety research community), discussing the need for research in overlooked areas, or pointing out structural issues that present obstacles to those who would otherwise do good research.

Reviewing and Submission Policy

Submissions are non-archival. We are happy to receive submissions that are also undergoing peer review elsewhere at the time of submission, but we will not accept submissions that have already been published or accepted for publication at peer-reviewed conferences or journals. Submission is permitted for papers presented or to be presented at other non-archival venues.

Most accepted papers will be offered a poster presentation. We are also accepting in absentia paper submissions, should you be unable to attend in person.

TAIS 2026 is not peer-reviewed. Our team of editors will review each submission and decide whether to accept a paper as a poster, invite the authors to lead a workshop, or reject it. Evaluation of submissions will be based on originality and novelty, technical strength, and relevance to the workshop topics. Notifications of acceptance will be sent to applicants by email.