Democratizing AI scientists with ToolUniverse
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
A multi-agent AUTO Research loop for idea discovery, experiment execution, evidence-grounded paper writing, quality audit, and live Web observation from AI group, CNIC, CAS.
We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference modeling and alignment problem.
(ACL-2025 main conference) Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Where AI discovery becomes science
Runtime AI Scientist (formerly RAC AI Scientist): official code for "Can AI Scientists Coordinate at Runtime?" (arXiv 2610.00980). Runtime Agent Coordination (RAC) for multi-agent AI scientists such as ARK, Agent Laboratory, and EvoScientist, evaluated on ResearchClawBench.
Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station
Automate the full research workflow from paper reading to experiment execution and peer-review for machine learning models on consumer GPUs.
AI/DeepLearning Star Scientists