AI makes AI better.

5 picked from 73 candidates · 30 sources read · 74 loops indexed

1. 01
   Loop of the dayPaperarXiv30 Oct 2026Tools and harness

   RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory

   The loop: A coding model observes a robot's rollouts, diagnoses failures, and iteratively revises the control harness around a frozen policy. This evolved harness then wraps the policy to improve the agent's success rate on unseen scenes and tasks.

   RoboArchitect demonstrates that a coding model can iteratively rewrite the control harness around a frozen policy, offering a powerful alternative to finetuning for adapting agents to new environments.

   loop fit 9/10Shengguang Wu, Suning Huang et al.via arXiv
   
2. 02
   PaperarXiv2 Nov 2026Architecture and optimizer search

   MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery

   The loop: The MoLRSI agent optimizes its own molecular discovery workflows and model architectures based on execution feedback. It stores the refinement outcomes in a persistent memory to improve its strategy for developing workflows in subsequent searches.

   loop fit 9/10Yikun Zhang, Xiwei Cheng, Mingze Yuan, Yu Zhang, Brian Shim, Aarti Krishnan,...via arXiv
   
3. 03
   ProjectGitHub31 Oct 2026Self-modifying agents

   dxn111/EVOLV

   The loop: The EVOLV workspace rewrites its own user interface, tools, skills, and plugins during execution. These modifications directly alter the environment it operates within, enabling immediate use of the new capabilities.

   loop fit 8/10dxn111via GitHub
   
4. 04
   Forum postLessWrong1 Nov 2026Interpretability and oversight

   Monitor Evasion Depends on What RL Finds and What Monitors Miss

   The loop: The study identifies how RL learns to exploit monitor blind spots, which improves the training process by informing weight edits that prevent monitor evasion.

   loop fit 7/10Pranjal Gargvia LessWrong
   
5. 05
   PaperarXiv29 Oct 2026Interpretability and oversight

   Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement

   The loop: Safin-1.5 uses a discovery-evaluation-repair loop to identify new risks and generate repair data. This data is then used to update its own safety architecture and removable experts, improving its intrinsic safety.

   loop fit 8/10Jingnan Zheng, Cheng Jin et al.via arXiv
   
6. 06
   PaperarXiv29 Oct 2026Training data

   Search-Guided Reasoning Trace Curation for Verilog Generation

   The loop: A search framework explores intermediate hardware design plans to curate reasoning traces. These traces are then used as supervised fine-tuning data to improve the Verilog generation model that performs the search.

   loop fit 8/10Liaoyuan Fan, Yuhao Zheng et al.via Hugging Face Papers
   
7. 07
   PaperarXiv29 Oct 2026Self-reward and self-play

   Predict the Reward, Not the World: World Reward Models for ML Agents

   The loop: A world reward model learns from real execution results to directly choose the best candidate programs written by an ML agent. This model then replaces slow execution steps in the agent's search, making the agent faster and more accurate at finding optimal programs.

   loop fit 8/10Ruoyu Wu, Zengji Tu et al.via arXiv
   
8. 08
   PaperarXiv29 Oct 2026Tools and harness

   Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement

   The loop: An agent harness coordinates video models and world models to generate interactive environments. These models then mutually evaluate and improve one another, enhancing the harness's ability to produce coherent agentic video generation.

   loop fit 8/10Chengyu Yang, Yunxiang Zheng et al.via arXiv