10 papers
Towards End-to-End Automation of AI Research
Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5
The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific pr…
Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Jenny Zhang, Shengran Hu, Cong Lu +2
Today's AI systems have human-designed, fixed architectures and cannot autonomously and continuously improve themselves. The advance of AI could itself be automated. If done safely…
Learning to Continually Learn via Meta-learning Agentic Memory Designs
Yiming Xiong, Shengran Hu, Jeff Clune
The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limit…
SIMA 2: A Generalist Embodied Agent for Virtual Worlds
SIMA team, Adrian Bolton, Alexander Lerchner +63
We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a signifi…
Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models
Aaron Dharna, Cong Lu, Jeff Clune
Multi-agent interactions have long fueled innovation, from natural predator-prey dynamics to the space race. Self-play (SP) algorithms try to harness these dynamics by pitting agen…
How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks
Lapo Frati, Neil Traft, Jeff Clune +1
Recent work in continual learning has highlighted the beneficial effect of resampling weights in the last layer of a neural network (``zapping"). Although empirical results demonst…