Demonstrates large-scale agent deployment capabilities with long-running AI systems for researchers.
Third Moment Research runs 10,000 AI agents continuously for 36+ hours using GPT-6 models for cybersecurity applications.
With GPT-6 Astra and GPT-6.1 Sol, Codex, and Daybreak for cybersecurity, this AI lab builds agents that focus for days and improve with use.
Researchers introduce Tev, a novel training framework with dense progress rewards that enables 27B parameter models to match GPT-6 and Claude Opus 5 performance on long-horizon agentic tasks.
GUIDE is a multi-agent AI system that automates clinical guideline generation, achieving 88.85% literature recall and reducing expert workload by over 70% while maintaining expert-quality recommendations.
Researchers developed a data-free training method for diffusion models in lattice field theories using self-generated samples and target score identities.
ChunkAct introduces action chunking to agentic robotics, reducing LLM calls by 2.9x while improving task success by 5.0 points on LIBERO-Pro benchmark.
Researchers introduce AesCode, a method that improves aesthetic code generation for visual artifacts by using decoupled cross-modal rewards from both code verifiers and visual language models.
