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 →
12 picked from 2 candidates · 31 sources read · 76 loops indexed
- 01Loop of the day6 Nov 2026Inference efficiency
ServerBench: How can your coding agents design specialized LLM serving systems?
The loop: Coding agents design and optimize specialized LLM serving systems, which then run the agents themselves with higher efficiency and lower cost.
Coding agents optimizing the very serving infrastructure they run on is a perfect example of a tight, practical recursive loop.
- 02Research automation
ReproBridge: Building Reproducibility into ML Research Artifacts
The loop: The ReproBridge agent constructs reproducible research artifacts from raw code and papers, which improves the ability of successor agents to reproduce and build on ML research.
loop fit 9/10via Awesome-AI4AI
- 035 Nov 2026Self-reward and self-play
Better honeypots, fewer tries: training an optimizer to make PPO cheat
The loop: A learned optimizer searches for gridworld levels that induce reward-hacking, which improves the evaluation of PPO, which makes the training process better at identifying and fixing cheating.
- 042 Nov 2026Self-modifying agents
Toyhom/EvoSprig
The loop: EvoSprig uses visual workflows and multi-agent collaboration to enable agents to perform recursive self-improvement on their own tools and harnesses.
- 055 Nov 2026Tools and harness
Beneath the Surface: What We Overlook When We Talk About Agent Evolution
The loop: Agent harness evolution methods modify the agent's prompts and components, which improves task reliability and coverage, making the agent more effective at its tasks.
loop fit 9/10Shijue Huang, Hangyu Guo, Guanting Dong, Chenxin Li, Junting Lu, Xinyu Geng,...via arXiv
- 066 Nov 2026Tools and harness
TTHE: Test-Time Harness Evolution
The loop: Agentic proposers reason over execution traces to evolve the agent's harness at test time, which then improves the agent's own execution and success rate on subsequent tasks.
loop fit 8/10Ellen Xiaoqing Tan, Jack Lanchantin, Zichun Yu, Polina Kirichenko, Shehzaad...via arXiv
- 075 Nov 2026Self-reward and self-play
Better honeypots, fewer tries: training an optimizer to make PPO cheat
The loop: A learned optimizer searches for gridworld levels that induce reward-hacking, which improves the evaluation of PPO and makes the training process better at identifying and fixing cheating.
- 086 Nov 2026AI R&D evals
Auditing Harness Tampering in Self-Improving Agents
The loop: Self-improving agents attempt to modify their own code or environment, while an auditing system monitors for tampering to ensure the safety and reliability of the resulting improved agent.
loop fit 7/10Carel van Niekerk, Renato Vukovic, Benjamin Ruppik, Hsien-chin Lin, Shutong...via arXiv
Loop index
All 76 entries →
- Gemini models propose code changes
- Evaluators keep best scoring versions
- Finds better Gemini training kernels
- Lowers cost to train next Gemini models
- repeat
- Coding agent edits its own code
- Scored child agents enter the archive
- Archived agents make later self modifications
- repeat
- RL agent lays out TPU blocks
- Better layouts make AI hardware cheaper
- Agent pre-trains on earlier chip generations
- repeat
- Coding agent edits LLM training script
- Runs a 5-minute training job
- Keeps change if validation improves
- Changes transferred to larger models
- repeat
- Research agent writes harness mutation blueprints
- Coding agent implements harness module changes
- Winning harness becomes the new champion
- New champion harness runs further generations
- repeat
- Aligned model generates training data
- Reward model judges and filters it
- Data trains next intermediate instruct model
- Next model generates better alignment data
- repeat
- Model generates candidate responses to prompts
- Model scores them itself as a judge
- Scores become preference pairs for DPO
- Trained model becomes next generator and judge
- repeat
- Claude Code writes its own code changes
- Changes become next Claude Code versions
- Release becomes harness for next development round
- repeat
- LLM agents write and benchmark kernels
- Kernels speed up AI model training
- Session data post-trains smaller kernel models
- repeat
- Coding agent writes fine-tuning code
- Agent post-trains a base LLM
- Trained model scored on target benchmark
- One turn of model training another
- repeat
- Learned optimizers update other learned optimizers
- Training keeps best performing optimizer parameters
- Better optimizers train each other faster
- repeat
- LLM reads reasoning model thoughts
- LLM flags reward hacking behavior
- Signal feeds back into training reward
- Trains more aligned capable agents
- repeat
Support for loop research
How to apply →Grants
Funding for projects that put AI in the loop of making AI better. Rolling, low paperwork, sized to the work.
About grants →Fellowships
Funded time, compute and mentorship for researchers who want to go deep on one loop.
About fellowships →Compute
GPU time and credits for loop experiments, which almost always have to run more than once.
About compute →Have a loop worth building?
Tell us what the AI improves and how the improvement comes back. Applications for grants, fellowships and compute all start on the contact page.