Allen Institute for Artificial Intelligence (Ai2) Announces Launch of Asta: Accelerating Science Through Trustworthy Agentic AI

Ed. Note: For the many Ai2 users already out there:

• Paperfinder is part of the Asta ecosystem. It’s now the “Find Papers” tool/service.
• ScholarQA is also part of the Asta ecosystem. It’s the “Summarize Literature” tool/service.

From Ai2:

Today we announce Asta, our bold initiative to accelerate science by building trustworthy and capable agentic assistants for researchers, alongside the first comprehensive benchmarking system to bring clarity to the landscape of scientific AI. As AI use expands across the sciences, researchers in every field need helpful systems they can understand, verify, and trust. Asta is designed to fill this need.

The Asta ecosystem brings together three essential components to advance scientific AI. At its center are the Asta agents, tools to assist (not replace) human researchers performing complex, real-world scientific tasks.

To promote transparency and raise the bar across the broader landscape of scientific AI, AstaBench provides a rigorous, domain-relevant benchmarking framework for evaluating and comparing any agent—not just Asta.

And for AI developers,Asta resources offers a set of software components and standards to help build, test, and refine scientific AI agents.

Scientists remain skeptical—and AI researchers face a different challenge: without trusted standards, it’s hard to evaluate whether models are truly capable of the deep reasoning science demands.

For researchers, Asta offers agents designed to work the way scientists think—helping frame research questions, trace ideas to evidence, and clarify what’s established or still unresolved in a field. AstaBench ensures these agents are evaluated against real-world tasks, building trust and scientific rigor.

For those building scientific AI agents who need a reliable way to evaluate and improve their work, AstaBench and Asta resources provide a complete agent evaluation environment and tools to facilitate the creation of production-ready, state-of-the-art agents. AstaBench offers leaderboards and real-world benchmarks that make it easy to test, compare, and iterate on AI agents.

Asta resources includes our own open-source and baseline agents ready to fork and compare against, open language models post-trained on science, and modular tools enabling agents to perform scientific research tasks. These tools are easy to use via the Model Context Protocol (MCP) and support both reproducible, time-fixed evaluation and up-to-date real-world usage.

[Clip]

Our initial release of Asta includes three core functions:

• Find papers helps you discover relevant research using an LLM-powered search experience, like Google Scholar on steroids, that mirrors the multi-step reasoning process of expert researchers. It reformulates queries, follows citations, and explains why each paper is relevant, making it easier to find exactly what you’re looking for—even when keywords fail.
• Summarize literature turns complex research questions into structured, comprehensive summaries—every claim backed by a clickable citation and often an inline excerpt. It scans millions of abstracts and full-text papers, clusters evidence, and distills findings into clear sections that highlight key results, disagreements, and open questions.
• Analyze data (available in beta for select partners) turns natural language questions into structured, reproducible analyses. It explores your dataset, generates hypotheses, runs statistical tests, and explains the results—making data-driven discovery faster, clearer, and accessible across disciplines.

Learn Much More, Read the Complete Launch Announcement

Filed under: Data Files, Journal Articles, News, Patrons and Users