AI makes AI better.

8 picked from 129 candidates · 31 sources read · 70 loops indexed

1. 01
   Loop of the dayPaperarXiv23 Oct 2026Research automation

   SplatLab: Autonomous Scientific Discovery for 3DGS Research

   The loop: SplatLab autonomously reproduces baselines and proposes extensions for 3D Gaussian Splatting. It then uses an internal Elo tournament to score candidates on measured GPU PSNR, feeding verbal gradient feedback back into its own generation process to refine its research outputs.

   SplatLab demonstrates a fully autonomous research loop in a highly active computer vision subfield, using an internal Elo tournament to rigorously select and refine its own proposed extensions.

   loop fit 10/10Seemandhar Jain, Manmohan Chandrakervia arXiv
   
2. 02
   PaperarXiv22 Oct 2026Kernels and compilers

   CANNBot-CAKE: Collaborative Agentic Kernel Evolution for Ascend NPU

   The loop: The CAKE agent generates and evolves AscendC kernels for NPUs using a self-evolving architecture and reviewed knowledge reuse. This improves the performance of the custom operators it runs on, accelerating the hardware stack that supports the agent's own future workloads.

   loop fit 9/10Deng Pan, Xue-Jian Gao et al.via arXiv
   
3. 03
   Articlerecursive.com21 Oct 2026Training data

   Introducing Flint

   The loop: The Eureka Machine AI system generated the training data and optimized the quantization and inference stack for the Flint model. Flint is then deployed for local agentic coding, providing an open-weights tool to further automate AI development.

   loop fit 9/10via Awesome-AI4AI
   
4. 04
   Blog postAnthropic19 Oct 2026Interpretability and oversight

   Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents

   The loop: An AI red-teaming process is used to probe and identify vulnerabilities in the Auto Mode blocking classifier. The classifier is then updated based on these findings, improving its ability to safely oversee and constrain the actions of autonomous coding agents.

   loop fit 7/10via Anthropic Alignment
   
5. 05
   ModelHugging Face22 Oct 2026Self-reward and self-play

   Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox

   The loop: ThinkingBox automates the conversion of database grading outcomes into reinforcement learning rewards. These rewards are then fed back into the post-training pipeline to improve the performance of the agents executing the database tasks.

   loop fit 7/10via Hugging Face
   
6. 06
   PaperarXiv22 Oct 2026Training data

   LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data

   The loop: The LongZero model synthesizes complex questions, answers, and supporting evidence into a compact structured form before expanding them into a long multi-document context. It then uses this self-generated data for reinforcement learning, improving its own long-context reasoning capabilities without external data.

   loop fit 9/10Zhennan Wan, Jianfei Chenvia arXiv
   
7. 07
   PaperarXiv23 Oct 2026Tools and harness

   Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3

   The loop: A frontier model constructs a complete task harness for the ARC-AGI-3 benchmark and acts through it on development games. It then revises the entire codebase based on its performance, improving the orchestration of its own calls, memory, and tool use for future interactive tasks.

   loop fit 9/10Jens Lehmann, Sahar Vahdativia arXiv
   
8. 08
   PaperarXivAI R&D evals

   SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?

   The loop: Coding agents are evaluated on their ability to complete long-horizon, whole-repository stack migrations. This benchmark provides a direct measurement of AI performance on complex software engineering tasks, guiding the development of agents that can refactor and maintain their own codebases.

   loop fit 8/10via Awesome-AI4AI