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

30 Oct 2026Full radar →

6 picked from 64 candidates · 31 sources read · 73 loops indexed

01
Loop of the dayPaperarXiv28 Oct 2026Kernels and compilers
A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI Accelerator
The loop: An LLM agent loop builds a target knowledge base of DSL documentation and microbenchmarks to autonomously optimize decode kernels, which run the models that power the agent.
An LLM agent loop autonomously learns a new AI accelerator's DSL to optimize the very decode kernels that will run its successors.
loop fit 9/10Byonggon Chunvia arXiv
02
PaperarXiv28 Oct 2026Training data
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
The loop: A-RSI monitors its own training logs to decide when to refresh a task pool with model-authored programs, enabling continuous multimodal self-improvement without external data.
loop fit 10/10Yu Liu, Youxing Li et al.via arXiv
03
Blog postSakana AI30 Oct 2026Research automation
Intelligence Report: SNSのAI分析からみる米中間選挙
The loop: Sakana Marlin uses multiple AI agents to parallelize hypothesis search and evaluate each other, improving the accuracy and depth of the research reports it generates.
loop fit 7/10Sakana AIvia Sakana AI
04
PaperarXiv28 Oct 2026Tools and harness
Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents
The loop: An AI agent edits its own harness prompts and rules, using an automated gate to measure and retain improvements to its own operating environment.
loop fit 9/10Hau-Sing So, Daixian Liu et al.via arXiv
05
Blog postTogether AI27 Oct 2026Hardware and chips
Auto repair for Together GPU Clusters: from GPU fault to healthy node
The loop: The auto repair system detects and fixes GPU and fabric faults, which maintains the availability of the hardware used to train and run the system's successors.
loop fit 6/10via Together AI
06
PaperarXiv28 Oct 2026Self-reward and self-play
SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning
The loop: The SCOPE policy analyzes its own trajectories to generate step-specific hindsight skills, distilling their guidance back into itself at selected error steps.
loop fit 9/10Qirui Liu, Wei Cao et al.via Hugging Face Papers
07
PaperarXiv28 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.
loop fit 9/10Johnny Yu, Cyril Gorllavia arXiv
08
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