AI makes AI better.

7 picked from 2 candidates · 31 sources read · 70 loops indexed

1. 01
   Loop of the dayPaperarXiv22 Oct 2026Training data

   TeachBack: Learning to Teach via Bidirectional Preference Optimization for On-Policy Self-Distillation

   The loop: A Teacher model generates reasoning trajectories for a Student model, while using the Student's learning progress to optimize how the Teacher generates that data. This bidirectional optimization improves the quality of the training data and the resulting Student model.

   TeachBack demonstrates a closed loop where the student's learning progress directly optimizes the teacher's data generation, moving beyond static self-distillation.

   loop fit 9/10Linfei Ji (Huazhong University of Science and Technology), Jiayun Li (Tsinghua...via arXiv
   
2. 02
   PaperarXiv23 Oct 2026Self-modifying agents

   Agentic Knowledge-Model Co-Evolution via Consistency Regularization

   The loop: The SPLICE framework analyzes agent experience to produce knowledge candidates, which improves the internal model through self-distillation. This makes the agent better at analyzing future experiences and solving tasks.

   loop fit 9/10Sirui Chen, Zhining Liu, Chao Zhang, Jingrui He, Zheng Livia arXiv
   
3. 03
   ProjectGitHub8 Aug 2026Self-modifying agents

   i3T4AN/KADATH

   The loop: An evolutionary runtime breeds and evaluates autonomous agents, which improves their goal optimization performance. This makes the successor agents better at the same task in subsequent epochs.

   loop fit 7/10i3T4ANvia GitHub
   
4. 04
   PaperarXiv22 Oct 2026Inference efficiency

   RCSD: Reinforcement and Continual Learning for Domain-Specific Speculative Decoding

   The loop: A speculative decoding system uses sequences generated during inference to construct preference pairs that train the draft model. This alignment improves the draft model's acceptance length, making the overall inference system faster.

   loop fit 9/10Mingkang Liu, Weiming Meng, Peipei Jiao, Jiawei Zhang, Tianyuan Liu, Junyan...via arXiv
   
5. 05
   PaperarXiv21 Oct 2026Tools and harness

   HGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning

   The loop: The HGM-Dual framework uses lineage-aware context to optimize an agent's harness, which improves the agent's planning performance. This improved performance provides better edit outcome attribution for the next round of harness optimization.

   loop fit 9/10Sudipta Paul, Pengrui Quan et al.via arXiv
   
6. 06
   PaperarXivTools and harness

   Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

   The loop: The Harness-of-Harness system performs autonomous software development while continually improving its own harness. This improved harness makes the system better at further autonomous development.

   loop fit 8/10via Awesome-AI4AI
   
7. 07
   PaperarXivSelf-reward and self-play

   Self-Play Pretraining with Zero Data

   The loop: The model engages in self-play to generate its own training data. This data improves the model's weights, making the model better at future self-play and task performance.

   loop fit 8/10via Awesome-AI4AI
   
8. 08
   PaperarXiv21 Oct 2026AI R&D evals

   VeriEvolve: Evaluator-First Evolution for Tool-Using Agents

   The loop: VeriEvolve constructs and revises its own executable evaluator using agent run outcomes, which provides a better fitness signal for the next round of agent evolution.

   loop fit 9/10Yueshen Li, Kamer Ali Yuksel et al.via arXiv