AI makes AI better.

11 picked from 74 candidates · 29 sources read · 74 loops indexed

1. 01
   Loop of the dayPaperarXiv1 Nov 2026Tools and harness

   Exo: An Architecture for Self-Improving Systems at Runtime

   The loop: The Exo agent autonomously edits its own harness code and strategies during task execution. These inspectable code changes are preserved and activated to reduce costs and improve performance on subsequent tasks.

   Exo collapses the optimization loop directly into task execution, allowing agents to rewrite their own harnesses on the fly.

   loop fit 9/10Chaoyun Zhang, Bingxuan Li et al.via arXiv
   
2. 02
   PaperarXiv2 Nov 2026Tools and harness

   TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents

   The loop: Frontier agents propose and statistically validate edits to a teacher model's harness. The improved harness is then used to collect successful trajectories to distill a compact student agent that operates in that same evolved harness.

   loop fit 9/10Yanbei Jiang, Chao Lei et al.via arXiv
   
3. 03
   ReleaseGitHub2 Nov 2026Interpretability and oversight

   Training activation classifiers for safety and alignment

   The loop: Activation classifiers monitor a model's internal activity to detect policy violations. This improves the safety and alignment of the model, making it safer to deploy and use for further development.

   loop fit 7/10codelionvia GitHub releases
   
4. 04
   Blog postOpenAI2 Nov 2026Interpretability and oversight

   Training activation classifiers for safety and alignment

   The loop: Activation classifiers monitor a model's internal activity to detect policy violations, which improves the safety and alignment of the model, which makes the model safer to deploy and use for further development.

   loop fit 7/10Alex Makelov, Xiaojun Xu, Sundaram Ananthanarayanan, Ethan Mcdonald, Tom Dupre...via OpenAI Alignment
   
5. 05
   PaperarXiv30 Oct 2026Self-reward and self-play

   CARE: Grounded Recursive Self-Improvement for Production Customer-Service Agents

   The loop: The CARE agent identifies its own production failures and pairs them with independently verified repairs. It then uses on-policy self-distillation to update its own weights, improving its performance on future customer service traffic.

   loop fit 9/10Kehong Gong, Xiaoxu Zheng et al.via Hugging Face Papers
   
6. 06
   Blog postOpenAI2 Nov 2026Tools and harness

   Scaling Git at OpenAI

   The loop: Codex generates code at a scale that necessitates a new Git backend, which improves the development infrastructure for OpenAI models, which makes the development of Codex and its successors more efficient.

   loop fit 6/10via OpenAI
   
7. 07
   PaperarXiv30 Oct 2026Self-modifying agents

   Evolving Memory, Learning to Meta-Control: Test-Time Adaptation for Experience-augmented LLM Agents

   The loop: The OMCE meta-controller uses task feedback to update its memory bank and refine its own routing policy via contextual bandit updates. This improves how the agent retrieves and utilizes experience in future tasks.

   loop fit 9/10Jun He, Canmiao Fu et al.via arXiv
   
8. 08
   PaperarXiv31 Oct 2026Research automation

   algorithmicsuperintelligence/openevolve: v0.4.1

   The loop: The OpenEvolve framework uses mixed evolution modes and competitive checkpoints to iteratively refine programs. It records the mode used on each program in an evolution trace to improve the evolution process.

   loop fit 8/10Yandan zheng, Haoran Luo et al.via arXiv