CodeAgent
End-to-end execution for real-world coding tasks, enabling agents to autonomously understand, modify, and run complex repositories.
CodeAgent · DeepResearch · Agentic RL · Self-Evolving Systems
End-to-end execution for real-world coding tasks, enabling agents to autonomously understand, modify, and run complex repositories.
Multi-step reasoning agents for open-ended scientific and knowledge discovery, synthesizing insights across domains.
Reasoning-centered reinforcement learning, bridging decision-making, planning, and adaptive intelligence.
Agents that continuously improve through self-evolution and collaborative learning, enabling emergent collective intelligence.
Agent-driven automated investment: discovering optimal factors, strategies, and execution models for intelligent trading and portfolio management.
Efficiency-first AI for healthcare: scalable foundation models, vision-language alignment, and agentic workflows for real-world clinical impact.
Agent-driven discovery in genomics: automating bioinformatics analyses and enabling novel scientific insights in biological research.
Switch between the strongest publications, commercialized systems, and media coverage without leaving the homepage.