AI makes AI better.

9 picked from 106 candidates · 31 sources read · 74 loops indexed

1. 01
   Loop of the dayPaperarXiv5 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.

   EvoOptiGraph demonstrates a closed co-evolutionary loop where a model actively targets its own weaknesses to generate the next generation of its training data.

   loop fit 10/10Qingcan Kang, Mingyang Liu, Xiaojin Fu, Shixiong Kai, Tao Zhong, Mingxuan Yuanvia arXiv
   
2. 02
   PaperarXiv2 Nov 2026Inference efficiency

   SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding

   The loop: Parallel agents explore algorithm and system optimizations for speculative decoding deployments. Successful optimizations are integrated to accelerate the target model's own inference.

   loop fit 9/10Kunjun Li, Wenhao Chai et al.via Hugging Face Papers
   
3. 03
   Blog postTogether AI4 Nov 2026Kernels and compilers

   Together Compiler: Continual Compilation for AI inference

   The loop: AI agents continuously optimize inference kernels for open models based on changing traffic. The resulting compiled kernels are then deployed to run those same models with higher throughput.

   loop fit 8/10via Together AI
   
4. 04
   PaperarXiv4 Nov 2026Tools and harness

   Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement

   The loop: A coding agent proposes patches to its own memory harness based on failure traces, while a critic screens them for benchmark gaming. Accepted patches permanently update the harness, improving the agent's performance on future conversations.

   loop fit 9/10Sen Yang, Jiaduo Lin et al.via arXiv
   
5. 05
   Blog postNVIDIA4 Nov 2026Tools and harness

   Use NVIDIA NeMo to Turn Agent Failures into Tests and Harness Fixes

   The loop: Agents analyze their own production failures to generate custom evaluations and propose harness fixes. These fixes are then applied to improve the agent's prompts, memory, and execution code.

   loop fit 8/10Patrick Moorheadvia NVIDIA Technical Blog
   
6. 06
   PaperarXiv5 Nov 2026Architecture and optimizer search

   Evolutionary System Prompt Learning for Reinforcement Learning in LLMs

   The loop: The language model samples trajectories under multiple system prompts, using them to update its weights via reinforcement learning and evolve its system prompts via self-reflection. Both the updated weights and the evolved prompts are then used by the model in the next iteration.

   loop fit 9/10Lunjun Zhang, Ryan Chen, Bradly C. Stadievia arXiv
   
7. 07
   PaperarXiv4 Nov 2026AI R&D evals

   From AutoResearch to Continual AutoResearch: Do Agents Learn Across Tasks?

   The loop: Research agents retain insights and persistent state across multiple machine learning tasks. This memory allows them to apply prior discoveries to new problems, improving their own research efficiency and solution quality over time.

   loop fit 9/10Jeremy Qin, Ruizhi Deng, Mohamed Osama Ahmed, Frederick Tung, Leo Fengvia arXiv
   
8. 08
   PaperarXivTraining data

   LegoEnv: Self-Evolving Agentic Environments via Modular Recombination

   The loop: LegoEnv enables the self-evolution of agentic environments through modular recombination, creating new training data and benchmarks for agent development.

   loop fit 8/10via Awesome-AI4AI