Sep 2, 2025
We apply end-to-end reinforcement learning to Biomni agent, creating rewards and RL environments tailored to biomedicine, scalably training the agent to carry out research tasks more effectively.
Jul 30, 2025
We present CRISPR-GPT, an LLM agent system to automate and enhance CRISPR-based gene-editing design and data analysis. CRISPR-GPT leverages the reasoning capabilities of LLMs for complex task decomposition, decision-making and interactive human–artificial intelligence (AI) collaboration.
Jul 17, 2025
Here we introduce POPPER, an agentic framework for rigorous automated validation of free-form hypotheses. Guided by Karl Popper's principle of falsification, Popper validates a hypothesis using LLM agents that design and execute falsification experiments targeting its measurable implications.
BioLab: End-to-End Autonomous Life Sciences Research with Multi-Agents System Integrating Biological Foundation Models
biorxiv
Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning
arxiv
Uncertainty Quantification over Graph with Conformalized Graph Neural Networks
NeurIPS 2023, Spotlight
Machine-learning-optimized Cas12a barcoding enables the recovery of single-cell lineages and transcriptional profiles
Molecular Cell
dCas9-based gene editing for cleavage-free genomic knock-in of long sequences
Nature Cell Biology
