AI makes AI better.

A daily hub for work where AI is part of the loop that improves AI, each entry with its loop spelled out. Read more →

1/4

A loop in motion

Project · Google DeepMind

Gemini models propose code changes

From the labalphaBell Qwen Open27B post-training research, with capability tradeoffs measured.Explore the model → From the labModel ObservatoryMeasured Flint and Qwen traces with published decoder maps.Open the lab tool → From the labMiniMax Video BudgetVisualize sampled frames, two-frame groups and vision placeholders.Try the inspector → From the labMOSS Blind Layout CheckCompare exact text and placement in two local images.Try the blind check → From the labAgent Request Evidence LadderSee what a trace proves about an agent's request and its outcome.Explore the cases →

Today's radar

29 Oct 2026Full radar →

12 picked from 10 candidates · 31 sources read · 73 loops indexed

01
Loop of the dayPaperarXiv28 Oct 2026Research automation
Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players
The loop: AutoTavern uses LLM research agents to build a game simulator and policy from live feedback, which improves their shared research memory and process, making the agents better at researching the game.
AutoTavern demonstrates how specialized LLM agents can autonomously research, build, and refine a complex game simulator and policy entirely from live feedback.
loop fit 9/10Johnny Yu, Cyril Gorllavia arXiv
02
PaperarXiv24 Oct 2026Tools and harness
When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement
The loop: RuHarness discovers behavioral criteria from execution trajectories to update its own harness, which improves the supervision used to guide the agent's future execution.
loop fit 9/10Changlian Ma, Limin Wangvia arXiv
03
ProjectGitHub23 Oct 2026Self-modifying agents
7-e1even/Cognitive-Enzyme-oss
The loop: Cognitive-Enzyme-oss captures agent experience and refines its memory layer through feedback, which improves the agent's lessons, making the agent better at future tasks.
loop fit 7/107-e1evenvia GitHub
04
Blog postNVIDIA26 Oct 2026Tools and harness
How NVIDIA Mission Control 2.5 Brings Autonomous Recovery to Kubernetes
The loop: NVIDIA Mission Control provides autonomous recovery for GPU clusters, which improves the reliability and efficiency of training large-scale AI models.
loop fit 7/10Elizabeth Goodmanvia NVIDIA Technical Blog
05
PaperarXiv27 Oct 2026Training data
MTA-Zero: Self-Improving Multimodal Deep Search via Online QA-Solver Co-training
The loop: A QA Generator creates verified questions at the Solver's learning frontier, which improves the Solver's training data, while the Solver's performance rewards and improves the Generator.
loop fit 9/10Hao Chen, Yukun Yan et al.via arXiv
06
PaperarXiv25 Oct 2026AI R&D evals
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
The loop: Change2Task converts historical pull requests into verified tasks, which provides executable data to train and evaluate the next generation of coding agents.
loop fit 9/10Wenhang Shi, Yiren Chen et al.via arXiv
07
PaperarXiv24 Oct 2026Self-modifying agents
7-e1even/Cognitive-Enzyme-oss
The loop: Cognitive-Enzyme-oss captures agent experience and refines its memory layer through feedback, which injects relevant lessons back into the agent's context, making it better at future tasks.
loop fit 7/10Dianxing Shi, Dingjie Fu et al.via arXiv
08
PaperarXiv27 Oct 2026Hardware and chips
How NVIDIA Mission Control 2.5 Brings Autonomous Recovery to Kubernetes
The loop: NVIDIA Mission Control provides autonomous recovery for GPU clusters, which improves the reliability of the hardware infrastructure used to train future AI models.
loop fit 7/10Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng...via arXiv