AI makes AI better.

7 picked from 102 candidates · 31 sources read · 75 loops indexed

1. 01
   Loop of the dayNewsAlignment Forum5 Nov 2026Research automation

   METR: Independent Assessment of AI R&D Acceleration at Anthropic in October 2026

   The loop: Anthropic uses its own AI systems to automate parts of its pretraining, reinforcement learning, and model evaluation workflows. This automated R&D work accelerates the capability improvements of Anthropic's internal models, directly speeding up the development of their successors.

   METR's independent assessment provides the first concrete, third party measurement of AI accelerating AI R&D at a frontier lab, estimating a 2x speedup in capability improvement.

   loop fit 9/10Zach Stein-Perlmanvia Alignment Forum
   
2. 02
   PaperarXiv6 Nov 2026Self-reward and self-play

   When Can Self-Play Fix a False Belief? Answer Keys, Pass Bands and Replacement Rules in an Execution-Grounded Loop

   The loop: Qwen3 4B Base generates output prediction tasks and Python code, then executes the code to derive answer keys. The model trains on these self generated, execution verified keys to correct its own planted false beliefs about task specifications.

   loop fit 10/10Nirdesh Chauhan, Dushyant Rajput, Siddharth Kosarajuvia arXiv
   
3. 03
   Blog postTogether AI4 Nov 2026Inference efficiency

   Polymorphic Inference: self-tuning inference for open models

   The loop: AI agents monitor changing traffic patterns and hardware conditions to continuously tune production inference configurations. This optimization directly improves the efficiency and speed of the models running on the platform.

   loop fit 8/10via Together AI
   
4. 04
   ProjectGitHub4 Nov 2026AI R&D evals

   flex-rsi/rsi-bench

   The loop: Agents attempt to recursively improve their own external harnesses, prompts, and tool configurations. The benchmark evaluates these updates to measure how effectively the agents can evolve their own operating environments.

   loop fit 8/10flex-rsivia GitHub
   
5. 05
   PaperarXiv4 Nov 2026Inference efficiency

   CompressionBench: How can your coding agents compress LLMs?

   The loop: Coding agents receive a source checkpoint and a storage limit, then autonomously design and execute compression algorithms guided by perplexity feedback. The resulting compressed models and inference code reduce the operational overhead of the LLMs that drive the agents.

   loop fit 9/10Xinrui Zhong, Zhifeng Li et al.via arXiv
   
6. 06
   Blog postOpenAI4 Nov 2026Tools and harness

   A thousand fewer paths to root

   The loop: An autonomous pipeline searches for, validates, and generates patches for local privilege escalation vulnerabilities in the Linux kernel. Applying these patches secures the underlying operating system infrastructure that hosts the AI's own training and inference workloads.

   loop fit 7/10via OpenAI
   
7. 07
   PaperarXiv6 Nov 2026Self-modifying agents

   WeightLoop: Weight-Space Programming with Experimental Feedback

   The loop: GPT-6 Astra writes a parameter editing program that inspects a model's implementation and prediction errors. The program validates candidate edits using experimental feedback and writes the successful changes directly back into the model's weights, improving its accuracy on subsequent tasks.

   loop fit 9/10Mengran Li, Bo Li, Weijing Zhao, Chengyang Zhang, Boyu Zhang, Jinfeng Xu,...via arXiv
   
8. 08
   PaperarXiv5 Nov 2026Training data

   EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

   The loop: The model identifies its own weaknesses to guide the generation of structurally diverse training instances. These new instances are then used in a reinforcement learning stage to update the model's own weights.

   loop fit 10/10Qingcan Kang, Mingyang Liu, Xiaojin Fu, Shixiong Kai, Tao Zhong, Mingxuan Yuanvia arXiv