RBC Borealis researchers earned first place in the AI Agentic Retrieval Grand Challenge at the 2025 ACM International Conference on AI in Finance (ICAIF) where the world’s leading AI teams tackle complex financial analysis challenges. The competition tested how well AI systems could find and interpret relevant information in complex financial filings.
This achievement demonstrates RBC’s commitment to building AI capabilities that don’t just keep pace with the industry but also help define where it’s headed and enable the enterprise to leverage AI across our businesses to enhance how our teams support our employees and clients.
The challenge: Finding signal in the noise
The competition focused on an issue that’s technically demanding and critically important: how do you help AI systems identify the right information in complex financial filings and use that information to deliver accurate, evidence-based answers?
In an industry where context matters, trust is paramount, and precision is non-negotiable, this capability represents a fundamental shift in how financial analysis can work at scale.
The solution: Smarter AI, better results
RBC Borealis’ winning approach was recognized for its innovative method to identify and prioritize relevant content within large volumes of complex financial documents - essentially teaching AI to read like an expert analyst.
The result? A solution that combines rigorous research with practical application.
“Some of the ideas behind this work were informed by challenges we were already exploring internally,” says Siqi Liu, Machine Learning Research Team Lead, RBC Borealis. “That gave us a strong foundation going into the competition and helped us build on research that was already grounded in real-world financial problems.”
What this win means
This recognition reflects more than technical excellence. It showcases the depth of AI talent and research capability RBC is building including the bank’s broader commitment to advancing AI in ways that create value for clients, strengthen the financial system, and push the industry forward.
It also reinforces RBC’s position as a leader in AI for finance, through adoption and foundational research that shapes what’s possible.
“This win reflects the research excellence and technical depth being built at RBC,” says Eric He, Research Director, RBC Borealis. “It shows our commitment to advancing AI in ways that strengthen the bank, support future innovation, and reinforce RBC’s leadership as one of the foremost voices on artificial intelligence in Canada and globally in financial services.”
The team behind the win
The first-place team combined deep expertise, creative problem-solving, and collaborative excellence:
This achievement demonstrates RBC’s commitment to building AI capabilities that don’t just keep pace with the industry but also help define where it’s headed and enable the enterprise to leverage AI across our businesses to enhance how our teams support our employees and clients.
The challenge: Finding signal in the noise
The competition focused on an issue that’s technically demanding and critically important: how do you help AI systems identify the right information in complex financial filings and use that information to deliver accurate, evidence-based answers?
In an industry where context matters, trust is paramount, and precision is non-negotiable, this capability represents a fundamental shift in how financial analysis can work at scale.
The solution: Smarter AI, better results
RBC Borealis’ winning approach was recognized for its innovative method to identify and prioritize relevant content within large volumes of complex financial documents - essentially teaching AI to read like an expert analyst.
The result? A solution that combines rigorous research with practical application.
“Some of the ideas behind this work were informed by challenges we were already exploring internally,” says Siqi Liu, Machine Learning Research Team Lead, RBC Borealis. “That gave us a strong foundation going into the competition and helped us build on research that was already grounded in real-world financial problems.”
What this win means
This recognition reflects more than technical excellence. It showcases the depth of AI talent and research capability RBC is building including the bank’s broader commitment to advancing AI in ways that create value for clients, strengthen the financial system, and push the industry forward.
It also reinforces RBC’s position as a leader in AI for finance, through adoption and foundational research that shapes what’s possible.
“This win reflects the research excellence and technical depth being built at RBC,” says Eric He, Research Director, RBC Borealis. “It shows our commitment to advancing AI in ways that strengthen the bank, support future innovation, and reinforce RBC’s leadership as one of the foremost voices on artificial intelligence in Canada and globally in financial services.”
The team behind the win
The first-place team combined deep expertise, creative problem-solving, and collaborative excellence:
- Siqi Liu, Machine Learning Research Team Lead
- Amin Shabani, Machine Learning Researcher
- Mohammed Suhail, Senior Machine Learning Researcher
- Shuvendu Roy, Machine Learning Research Engineer
