About The Workshop
The workshop aims to foster collaboration and stimulate innovation towards the development of next-generation AI research assistants that are reliable, transparent, and seamlessly integrated into the fabric of scientific discovery. Recent advancements in generative AI and agentic systems have unlocked the potential to automate and accelerate every stage of research, from hypothesis generation to paper writing. The rapid advancement of AI-assisted scientific research also brings social and ethical challenges. This workshop aims to advance the frontier of AI-assisted scientific research. Through a series of keynotes, panels, invited talks, paper presentations, and poster sessions, participants will have the opportunity to engage in cross-disciplinary discussions, share innovative ideas, and collaborate on solutions to current challenges.
Topics
The workshop will cover a range of topics, including but not limited to:
- Theoretical frameworks and system designs for autonomous research agents.
- Autonomous research systems that integrate multi-modal information (text, images, structural data) with external tools.
- Case studies of AI assistants conducting scientific research.
- Creation of large-scale, structured datasets for training and evaluating AI assistants and agents for scientific research.
- Novel benchmarks for end-to-end research tasks and specific scientific tasks, including automated literature review generation, experimental design, and scientific hypothesis generation.
- Quantitative and qualitative methods for evaluating the quality of AI-generated content.
- Frameworks for assessing reproducibility, interpretability, and robustness in AI-assisted research.
- Exploration and comparison of different models of human-AI collaboration in the research workflow.
- Design of novel user interfaces and workflows that support seamless human-AI interaction in a scientific context.
- Studies on how AI tools influence the cognitive processes of human researchers.
- Identification and mitigation of biases and hallucinations that AI may introduce or amplify in scientific research.
- Ethical frameworks and safety guardrails for ensuring transparency, interpretability, and reproducibility in AI-driven research.
- Perspectives and discussions on the evolving role of AI in scientific discovery.
Call For Papers
Key Dates
- Submission Deadline: November 18, 2025 (AOE)
- Notification of Acceptance: December 11, 2025 (AOE)
Submission Format
All papers must be submitted in PDF format, using the AAAI-26 author kit. We welcome two types of papers:
Full papers: Full-length research papers from 4 to 7 pages (excluding references and appendices).
Short papers: Research/position papers of up to 4 pages (excluding references and appendices).
Submission Site
The workshop uses OpenReview for paper submission and review. The submission link is https://openreview.net/group?id=AAAI.org/2026/Workshop/AI4Research.
The review process will be single-blinded, and we welcome accepted and published papers. The contributions will be non-archival and only will be hosted on our workshop website. There will be one best paper award for accepted papers with outstanding quality.
Accepted Papers
Invited Speakers
Schedule
To be announced
Organizers
This workshop is organized by
