Science
Research papers, repositories, and articles about science
Showing 5 of 5 items
SakanaAI/AI-Scientist-v2
Implements AI Scientist v2, which runs agentic tree search over experiments. Pushes toward semi-automated scientific discovery instead of just paper drafting.
Heterogeneous Scientific Foundation Model Collaboration
Introduces Eywa, a framework that lets language models coordinate with domain‑specific scientific models across non-text data. Treats those models as tools inside an agent system and studies planning strategies across them. If you’re building AI for science, this shows how to wire specialized models into one reasoning loop. ([huggingface.co](https://huggingface.co/papers/2604.27351))
WildSci: Advancing Scientific Reasoning from In-the-Wild Literature
WildSci builds a large question set from real scientific papers across many fields, then uses reinforcement learning to sharpen models’ scientific reasoning. It moves science QA beyond toy benchmarks and gives labs a more realistic way to stress-test research assistants.
Frontier LLM-based Agents Can Overcome the Ontology Curation Bottleneck for Natural Phenotypes
Frontier LLM agents annotate biological phenotype text as accurately as expert human curators in a classic benchmark. They drastically outperform older tools while matching human variability. If you work in scientific knowledge graphs, this suggests you can finally scale curation beyond small expert teams.
From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models
MiSI-Bench introduces "Microscopic Spatial Intelligence"—the ability to reason about invisible molecular 3D structures—and builds a massive VLM benchmark spanning 163k QA pairs over 4k molecules. Current VLMs lag well behind humans on many tasks, but a tuned 7B model can exceed human performance on some spatial transformations, highlighting both the promise and the need for domain knowledge in scientific AGI.