Algorithmic
Research Group
We study how software and industrial systems recursively improve themselves in real-world settings.
// Research
Study Failure: AI-driven GPU Kernel Optimization
A retrospective on 131,520 GPU kernel optimization attempts that were invalidated when agents were found to be substituting high-level...
Learning to Rank Architectures: A Small Model That Guides Neural Architecture Search
A tiny recursive reasoning model trained to rank architectures by predicted performance achieves 8-10x sample efficiency over random...
ARIA Benchmark: How Much Machine Learning Do AI Models Actually Know?
A suite of five closed-book benchmarks probing the ML knowledge that frontier language models have internalized during training.
ArXiv Research Code Dataset: 129K Research Repositories
A collection of 4.7 million code files from 129K research repositories linked to arXiv computer science papers.
ArXivDLInstruct: 778K Research Code Functions for Instruction Tuning
A dataset of 778,152 functions extracted from arXiv-linked research code, each paired with instruction prompts, for training...
DeltaMLBench: Can AI Agents Improve on Published ML Research?
A benchmark of 50 tasks drawn from real Papers With Code repositories where agents must achieve measurable improvement over published baselines.
Teaching Models to Bluff: Measuring Deception, Belief, and Coordination in LLM Secret Hitler
We implemented five LLM agents playing the social-deduction game Secret Hitler with structured logging to quantify deception, belief...
ML Research Benchmark: Can AI Agents Do Real ML Research?
A benchmark suite of 7 competition-level ML challenges for evaluating whether AI agents can perform genuine research iteration beyond...
// About
Recursive self-improvement is beginning to shape both software and industry. In software, AI systems are increasingly involved in designing, training, and optimizing other AI systems. Progress compounds through algorithmic advances and improvements in computing hardware.
In the physical world, similar dynamics are emerging in robotics, manufacturing, and supply chains, where automated systems increasingly optimize the processes that produce, deploy, and refine them.
Algorithmic Research Group studies recursive systems in practice. We measure progress, develop tools, and analyze how recursive improvement changes the behavior and capabilities of real-world systems.
Our work focuses on understanding the dynamics, limits, and impacts of self-improving systems across software and industrial domains.