cs.AINov 19, 2026

System-One RSI: Building Muscle Memory for Interactive Agents through Guided Practice

Authors: Qingxu Fu, Xuanfa Jin, Ziqian Chen, Zhaoyang Liu, Bolin Ding

Organizations: Alibaba Token Foundry - Infra & Model RSI - EconML · Institute of Automation, Chinese Academy of Sciences

Abstract

Reasoning models provide strong multimodal task understanding but struggle with sub-second control because deliberation increases decision latency. Fast decision models can meet the response window, yet prompting and few-shot examples do not readily provide the fine-grained experience required by a new task. Inspired by coached motor learning, this paper presents System-One Recursive Self-Improvement (System-One RSI), which couples two loops. The high-frequency online inner loop is an Observe, Orient, Decide, Act (OODA) cycle: a decision model maps each visual observation and task question to structured judgments, and a decision tree converts them into timed actions without invoking a reasoning model. The offline outer loop is a recursive improvement cycle carried out by a team of reasoning agents. The team revises the decision-model prompt and decision tree, captures interaction records, derives supervision from those records, and trains or deploys updated model parameters. The improved system then returns to the environment and generates the experience for the next round, consolidating learned distinctions as external muscle memory. The framework operates with a small number of real episodes, without expert demonstrations, environment modification, sandboxing, or parallel simulation. Experiments in Snake, Zenless Zone Zero, and Black Myth: Wukong use a 27B decision model. Mean Snake score increases from 1.30 to 7.35. In an evaluated scenario of Zenless Zone Zero, median completion time decreases by 8.4%. In an evaluated combat scenario of Black Myth: Wukong, the evasive policy achieves 11 times the mean survival time of a stationary reference, while the offensive policy win rate rises from 0% to 66.7% across the evaluated configurations.

Figures & tables

Explore similar work

CardsList
  1. Think Once, Act Fast: Cost-Effective Recursive Self-Improvement for Decision Model Harness

    Nov 17, 2026Siqi Lai, Haitao Li, Hao LiuLLM Agent Self-ImprovementLLM Decision-Making

  2. EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

    Oct 7, 2026Python Song, Zhixuan Liang, Kelsey Fu +3Continual Robot LearningRobot Skill Learning

  3. RSI-Env: An Open-Ended Environment for Recursive Self-Improvement of Agents

    Nov 1, 2026Wanying Qu, Zhiyuan Fan, Jiyao Liu +4LLM Agent Self-ImprovementRecursive Self-Improvement