AI makes AI better.

12 picked from 106 candidates · 31 sources read · 73 loops indexed

1. 01
   Loop of the dayPaperarXiv26 Oct 2026Research automation

   RSI Arena: Towards Recursive Self-Improvement with Human Feedback

   The loop: Training agents autonomously select data and train models, then receive human preference feedback on those models. The agents use this feedback to guide a second round of training, improving their own outputs.

   RSI Arena provides a crucial benchmark for autonomous post-training, measuring how well frontier models can act as ML engineers to train and refine their own successors.

   loop fit 9/10Xiaomi Embodied Intelligence Team, Yuechen Luo et al.via arXiv
   
2. 02
   PaperarXiv27 Oct 2026Self-reward and self-play

   How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning

   The loop: A student model identifies its own reasoning errors and writes critiques to condition a teacher version of itself. This teacher then distills the improved logic back into the student over a short rollout.

   loop fit 10/10Cheikh Ahmed, Zhiyu Zhang, Kun Mao, Yong Zhang, Zirui Zhouvia arXiv
   
3. 03
   ProjectGitHub22 Sep 2026Tools and harness

   e13ven-arch/reharness

   The loop: The reharness agent reads its own execution traces to rewrite its tools and skills, improving its performance on subsequent requests.

   loop fit 8/10e13ven-archvia GitHub
   
4. 04
   PaperarXiv26 Oct 2026Kernels and compilers

   Less is more: learning what to profile for GPU kernel optimization

   The loop: An LLM generates candidate modifications to a profiling tree based on feedback from GPU kernel optimization. The refined tree then provides more effective hardware information to the LLM for optimizing subsequent kernels.

   loop fit 9/10Wangcheng Tao, Zhanglu Yan et al.via arXiv
   
5. 05
   PaperarXiv27 Oct 2026Research automation

   Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players

   The loop: LLM research agents use live game feedback to improve a game simulator, opponents, and policy. They use this same feedback to refine their own research process and shared memory for future development.

   loop fit 9/10Yihan Wang, Peiyu Liu et al.via arXiv
   
6. 06
   PaperarXiv23 Oct 2026Tools and harness

   e13ven-arch/reharness

   The loop: An agent reads its own execution traces to rewrite its tools, hooks, skills, and prompts. It proves the changes with a live probe and adopts them to improve performance on future tasks.

   loop fit 8/10Yuhua Jiang, Chang Xu et al.via arXiv
   
7. 07
   PaperarXiv24 Oct 2026Self-modifying agents

   7-e1even/Cognitive-Enzyme-oss

   The loop: An AI agent captures its own experience and refines its memory layer through feedback. This refined memory injects more relevant lessons into the agent's context, improving its execution of future tasks.

   loop fit 7/10Yue Huang, Yanbo Wang et al.via arXiv
   
8. 08
   PaperarXiv27 Oct 2026Tools and harness

   Discovering and exploiting vulnerabilities in critical, real-world software with Claude

   The loop: Claude identifies critical vulnerabilities in widely used operating systems and browsers. Developers patch these flaws, securing the infrastructure that Claude itself relies on to operate.

   loop fit 7/10Jianwen Chen, Peng Xia et al.via arXiv