Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

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

Qingxu Fu, Xuanfa Jin, Ziqian Chen, Zhaoyang Liu +1 more

Published

Nov 19, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Nov 19, 2026

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

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.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Demonstrations

Directly usable for protocol triage.

"The framework operates with a small number of real episodes, without expert demonstrations, environment modification, sandboxing, or parallel simulation."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Reasoning models provide strong multimodal task understanding but struggle with sub-second control because deliberation increases decision latency."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Reasoning models provide strong multimodal task understanding but struggle with sub-second control because deliberation increases decision latency."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Reasoning models provide strong multimodal task understanding but struggle with sub-second control because deliberation increases decision latency."

Reported Metrics

strong

Win rate

Useful for evaluation criteria comparison.

"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."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

win rate
Human feedback details
Uses human feedback
Yes
Feedback types
Demonstrations
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Reasoning models provide strong multimodal task understanding but struggle with sub-second control because deliberation increases decision latency.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • 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.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Simulation environment) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Contribution summary

  • 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.

Why it matters for eval

  • In an evaluated scenario of Zenless Zone Zero, median completion time decreases by 8.4%.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Demonstrations

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: win rate