recursive

This paper develops two resource-efficient distributed recursive Gaussian process algorithms for multi-output regression in multi-agent systems, reducing communication overhead while maintaining estimation accuracy.

AutoMem is a text-gradient recursive self-improvement framework for automated memory architecture search in LLM agents, which discovers task-adaptive architectures that outperform human-designed baselines with improved accuracy and efficiency.

ReSyn is a generalized recursive framework for synthesizing regular expressions from examples, aiming to improve upon existing synthesis techniques.

Recursive releases an automated AI research system that achieves state-of-the-art results on three benchmarks: fixed-budget language model training, small-model training speed, and GPU kernel optimization. The system automates the research loop and open-sources artifacts from its runs.

The Recursive team released an automated AI research system that can autonomously complete the research loop, surpassing existing human community solutions on multiple benchmarks. For example, on NanoGPT Speedrun it compressed training time from 79.7 seconds to 77.5 seconds, and on SOL-ExecBench it improved the score to 0.754.

Recursive's automated AI research system achieves state-of-the-art results on NanoChat, NanoGPT Speedrun, and GPU kernel benchmarks by automating the research loop without task-specific adaptations, and open-sourcing artifacts for further inspection.

Former top researchers from OpenAI, DeepMind, and Meta jointly founded the startup Recursive, focusing on letting AI self-improve. In just 6 months with fewer than 30 people, they achieved a valuation of $4.65 billion.