Research
Methods, experiments, and ideas behind financial intelligence. View all articles
Latest article
Hindsight Structured Advice Distillation: Teaching a Small Model to Guide a Research Agent
A research agent's answer depends on more than the model behind it. The same agent, with the same tools and the same data, can…
Introducing FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents
Investors use Samaya's agent platform for challenging and open-ended work that spans their investment workflow: idea screening…
Before the Search: Why Query Understanding Matters for Financial Agents
Deep research agents are bottlenecked by information. The quality of an AI agent’s final answer depends not only on the agent’s…
Earlier stories
When Tool Documentation Falls Short: Teaching Agents to Learn From Interaction
At Samaya AI, we build agents for financial workflows that harness a wide range of tools to produce precise, analyst-grade…
Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search
At Samaya AI, we build deep research systems for complex questions that require exploring thousands of sources and reasoning…
Spotting Gaps Before They Matter: How Samaya Enhances Answer Accuracy in Real Time
Imagine you are a financial analyst preparing a quarterly market report. You ask Samaya a question like:
Criteria-Eval: Evaluating Long-form Answers to Complex Questions
After saturating component-wise evaluations of our question-answering system, we created a challenging end-to-end evaluation…
Promptriever: Elevating Retrieval Models with Instruction-Following Capabilities
At Samaya AI, our customers ask complex financial queries to quickly find accurate and comprehensive information. To support…
Evaluation of AI Agents at Samaya
Samaya is developing AI agents that dynamically compose models (e.g., retrievers, named entity disambiguators) to tackle…
Causal World Models: Bridging AI and Human Expertise
At Samaya, we are pushing the boundaries of reasoning systems by building causal world models that are designed to predict and…
The best AIs will be constructed, not emergent
As we approach two years since the launch of ChatGPT, and with the recent launch of o1, the AI ecosystem is evolving into its…
Can machines assist humans in verifying world knowledge?
For millennia humans have been producing knowledge. The advent of computers helped turn this knowledge into a digital format…
Information overload: the challenges of expanding context windows in large language models
Language models have demonstrated impressive performance for a variety of applications and use-cases, but limitations remain—for…
Does one large model rule them all?
The past 10 years have seen a constant stream of AI advances, with each new wave of developments enabling exciting new…
Bring the question behind your next decision.
See how Samaya handles a research question relevant to your team.
