AI makes AI better.

6 picked from 1 candidates · 31 sources read · 61 loops indexed

1. 01
   Loop of the dayPaperarXiv7 Oct 2026Self-reward and self-play

   Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models

   The loop: A Looped Language Model uses its own extended recurrent computation as a teacher to supervise its intermediate loops. Because the parameters are shared across all loops, distilling into the intermediate steps updates the shared weights, which immediately improves the terminal loop teacher for the next round of self-improvement.

   By sharing parameters across recurrent steps, LoopOPD elegantly turns a model's own extra compute into a direct, on-policy teacher for its earlier steps, creating a tight and continuous self-improvement loop.

   loop fit 9/10Yi Wang, Rui Qian et al.via arXiv
   
2. 02
   PaperarXiv8 Oct 2026Self-modifying agents

   Agentic-TTT: Training Test-Time Policy for Test-Time Training

   The loop: A language model learns a test-time policy to decide when and how to apply test-time training algorithms to itself. By training this policy on the utility gains observed from its past decisions, the model becomes better at managing its own parameter-level self-improvement during deployment.

   loop fit 9/10Jiahao Lu, Mohan Kankanhallivia arXiv
   
3. 03
   PaperarXiv7 Oct 2026Tools and harness

   CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution

   The loop: A terminal agent framework alternates between using execution failures to synthesize a better runtime harness and using verified rollouts to train the model policy. This co-evolution ensures that the model is trained on data matched to its adopted runtime, improving both the agent's weights and the harness it depends on.

   loop fit 9/10Jixuan Chen, Jiaxin Zhang et al.via arXiv
   
4. 04
   PaperarXiv9 Oct 2026Self-reward and self-play

   EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation

   The loop: A shared language model policy acts as both a reasoner generating responses and a generator creating evaluation rubrics. Discriminative feedback and peer consensus are used to improve the rubrics, which in turn provide better complementary rewards to optimize the shared policy for open-ended tasks.

   loop fit 9/10Xin Guan, Xiaomeng Hu, Shen Huang, Zhenyi Wang, Bo Zhang, Zijian Li, Pengjun...via arXiv
   
5. 05
   PaperarXiv9 Oct 2026Tools and harness

   DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration

   The loop: A full-duplex voice agent system uses interaction traces from simulated conversations to systematically revise its own harness modules. These revisions improve how the system coordinates task delegation and responsiveness, making the agent better at handling complex live collaborations.

   loop fit 9/10Yingda Shen, Yuxiang Wang, Kunyu Feng, Qinke Ni, Jiaqi Li, Minghao Hsu, Junan...via arXiv
   
6. 06
   PaperarXiv9 Oct 2026Architecture and optimizer search

   Neural Architecture Discovery via Autonomous Evolution

   The loop: The ASI-Arch system autonomously conducts neural architecture research through a closed loop process of experimenting, analyzing, and updating. This discovers novel architectures that can be used to train more capable base models, which in turn power future versions of the research agent.

   loop fit 8/10Weixian Xu, Yixiu Liu, Yang Nan, Lyumanshan Ye, Xiangkun Hu, Zhen Qin, Pengfei...via arXiv
   
7. 07
   PaperarXiv7 Oct 2026Training data

   AdvSim2Real: Training Web Agents Against Adaptive Prompt Injection in a Web World Model

   The loop: A web world model co-evolves a task curriculum and an injection adversary to train a web agent. The resulting training data improves the agent's robustness and capability, allowing it to handle more difficult tasks and stronger adversaries in the next iteration.

   loop fit 10/10Sarim Hashmi, Mukul Ranjan, Kshitij Mishra, Mikhail Kuznetsov, Praneeth...via arXiv
   
8. 08
   PaperarXiv6 Oct 2026Architecture and optimizer search

   RLDiscover: LLM-Driven Co-Evolution of Reinforcement Learning Algorithms

   The loop: The RLDiscover framework progressively co-evolves the components of model-free deep reinforcement learning algorithms. The discovered algorithms improve the learning efficiency of the agents that use them, providing better fitness signals for the framework to discover even stronger algorithms.

   loop fit 9/10Haoran Li, Zengle Ge et al.via arXiv