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
Figure 1: Successive observations of an attack in Black Myth: Wukong.
Approach
Advantages
Limitations
Online RL [ 10 , 11 ]
Learns policies from interaction feedback
Environment replication, reset, and parallel rollouts may be obstructed by external dependencies.
Offline RL [ 12 ]
Learns from existing trajectories
Data collection can be costly; coverage limits learning under distribution shift.
Reasoning-based computer use [ 1 , 5 ]
Applies task knowledge through deliberation
Repeated reasoning adds latency, and visual grounding can remain unreliable.
Reasoning-generated CV/control [ 7 , 8 ]
Converts task knowledge into executable rules
Perceptual conditions require specification and testing across visual edge cases.
Unadapted JEV [ 13 ]
Returns structured judgments without a reasoning trace
Pretrained capabilities may not cover the distinctions required by a new task.
JEV prompt optimization [ 13 , 9 ]
Revises instructions without parameter updates
Fine distinctions can be difficult to express; longer inputs increase processing cost.
Table 1: Routes to control capability and their constraints in live environments.
Figure 2: Guided practice as a model for learning external muscle memory.
Figure 3: Online control and recursive adaptation in System-One RSI.
Figure 4: Agent roles in controller revision and model adaptation.
Figure 5: Policy execution and model adaptation in Zenless Zone Zero.
Model
Top-1 (%)
Balanced accuracy (%)
NLL
Always none
86.15
33.33
N/A
zzz-rsi-base
63.85
44.52
0.6799
zzz-rsi-v1
79.23
74.87
0.4565
zzz-rsi-v2
81.15
77.98
0.4966
Table 2: ZZZ attack-warning validation.
Model
Wins
Median completion (s)
Median t50 (s)
p50/p95 (ms)
zzz-rsi-base
2/5
261.2
167.0
231.4/244.2
zzz-rsi-v1
5/5
236.2
26.0
229.1/249.4
zzz-rsi-v2
5/5
239.3
29.7
230.2/255.0
Table 3: ZZZ outcomes and decision latency.
Figure 6: Opponent-health trajectories in fifteen ZZZ episodes.
Figure 7: Mean completion time under two ZZZ controller configurations.
Opponent
zzz-rsi-v2 mean (s)
zzz-rsi-v3 mean (s)
YeShiyuan
242.7
159.3
Amalgam
207.2
190.8
Butcher
214.0
163.0
Pompey
245.0
194.0
Priest
309.0
293.0
Sweeper
278.0
242.0
Table 4: Completion times by opponent.
Figure 8: Policy execution and model adaptation in Black Myth: Wukong.
Figure 9: Recorded durations under the Wukong evasive policy.
Model
Episodes
Mean (s)
Median (s)
Stationary reference
6
23.6
N/A
wk-rsi-v1
10
108.1
114.9
wk-rsi-v2
10
160.0
170.1
wk-rsi-v3
5
160.9
166.7
wk-rsi-v4
5
260.5
212.2
Table 5: Wukong evasive-policy durations.
Figure 10: Visual observations during evasive control in Black Myth: Wukong.
Model
Episodes
Win rate (%)
Mean duration (s)
Winning mean (s)
wk-rsi-base
10
0.0
21.9
N/A
wk-rsi-v1
10
20.0
74.1
139.7
wk-rsi-v2
10
30.0
89.5
122.4
wk-rsi-v3
15
60.0
139.7
154
wk-rsi-v4
15
66.7
125.3
131
Table 6: Wukong offensive-policy outcomes.
Figure 11: Idealized timing of staggered inference and independent execution.