AI makes AI better.

9 picked from 134 candidates · 31 sources read · 60 loops indexed

1. 01
   Loop of the dayPaperarXiv9 Oct 2026Self-reward and self-play

   The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators

   The loop: A coder agent and a reviewer agent co-evolve under non-stationary utilities. The reviewer grades patches to guide the coder's search, while the coder's output helps the reviewer refine its grading rubric, making both better at their respective tasks.

   By co-evolving the coder and its evaluator, the Red Queen Gödel Machine escapes the bottleneck of static reward functions, allowing the evaluation criteria to scale alongside the agent's capabilities.

   loop fit 10/10Alex Iacob, Andrej Jovanovi\'c, William F. Shen, Daniel Burkhardt, Meghdad...via arXiv
   
2. 02
   PaperarXiv7 Oct 2026Kernels and compilers

   KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

   The loop: A multi-agent system profiles and optimizes generated Triton sub-kernels within compiled models. This improves the execution efficiency of the models and allows the agents to verify the re-stitched model end-to-end.

   loop fit 9/10Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal...via arXiv
   
3. 03
   ProjectGitHub24 Jun 2026Tools and harness

   Ker102/Harneloop

   The loop: Self-improving AI agents use trace-backed diagnosis and artifact-aware testing to refine their own harness units. This creates a better execution environment for their subsequent runs.

   loop fit 7/10Ker102via GitHub
   
4. 04
   Forum postLessWrong8 Oct 2026Interpretability and oversight

   J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses

   The loop: The J++ Lens provides more faithful readouts of model activations, which improves the ability to monitor and oversee the training of future models.

   loop fit 7/10Kola Ayonrindevia LessWrong
   
5. 05
   Blog postAnthropic8 Oct 2026Tools and harness

   An opt-in vulnerability-finding service for open-source software

   The loop: Claude scans open source software for vulnerabilities, which improves the security of the libraries Claude uses, making the system more robust.

   loop fit 6/10via Anthropic
   
6. 06
   PaperarXiv8 Oct 2026Research automation

   Language Models as AI Research World Models

   The loop: Language models act as Research World Models to predict the outcomes of candidate AI research experiments. This improves the selection of future interventions and generates new experimental data to further train the world model.

   loop fit 9/10Zijun Wang, Zewen Liu et al.via arXiv
   
7. 07
   ProjectGitHub6 Oct 2026Research automation

   richardcsuwandi/kernaut

   The loop: An automated research agent searches for novel GPU kernels. These kernels can then be used to discover and train more efficient architectures for future versions of the agent.

   loop fit 6/10richardcsuwandivia GitHub
   
8. 08
   PaperarXiv7 Oct 2026AI R&D evals

   RSIGym: A Flexible Environment for Recursive Self-Improvement

   The loop: AI research agents use a flexible environment to propose and evaluate changes to their own training data and execution harnesses. Successful interventions are then carried forward into subsequent improvement cycles, making the agents better at future research tasks.

   loop fit 9/10Fanqing Meng, Lingxiao Du et al.via arXiv