AIarXiv
Heuristic editor, no API keyVerdict: RoutineRSI-Anything: Unlocking Recursive Self-Improvement with World Models
Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve.
Key numbers
- 26.3% with a static verifier
- 29.2% through predictive selection and
- 31.2% after world-model adaptation
Caveats
- Preprint; not yet peer reviewed.
VerdictCompetent work. Briefs at most.
Abstract
Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a domain-general framework built on JEPA-Anything that uses predictive world models to guide action and learning-data selection. Observed feedback drives policy or workflow improvement and conditional world-model adaptation, while component and compatibility checks govern the retention of updated policy-model pairs. Across diverse computational and scientific domains, RSI-Anything demonstrates substantial gains. In code repair, with the coder fixed, success increases from 26.3% with a static verifier to 29.2% through predictive selection and 31.2% after world-model adaptation, at comparable test usage. Graphical user interface (GUI) evaluations showed higher task completion, while average actions decrease by 39.4%. Across five successive policy versions, laboratory-planning scores more than double from 21.80% to 46.01%. In reaction optimization, RSI-Anything achieves 96.15% mean best observed yield versus 82.16% for Bayesian optimization under the same 40-experiment budget. An end-to-end immune-science application further connects workflow evolution and predictive modeling with therapeutic hypothesis generation. These results demonstrate how predictive world models and retained system updates enable recursive improvement across diverse environments.
The editor's rubric
| Dimension | Level | Weight | What that level means |
|---|---|---|---|
| Leverage | ███░░ 3 | 24% | A method or resource many groups across the field will adopt within a year. |
| Magnitude | ███░░ 3 | 18% | Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem. |
| Evidence | ██░░░ 2 | 14% | Limited: single setting, weak baselines, or an observational association presented as causal. |
| Novelty | ██░░░ 2 | 16% | A new combination of known ideas. |
| Trajectory | ██░░░ 2 | 18% | Some room to improve with obvious engineering. |
| Stakes | ██░░░ 2 | 10% | Benefits a professional community (practitioners, clinicians, engineers). |
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); gains (relative gain); verification (code released); stakes (prevention or cure).
How the score was computed
- Merit
- 4.0 / 10
- Adjusted merit
- 4.0 / 10
- Attention
- 76%
- Freshness
- 46%
- Citations0 (reference 15, via semantic-scholar, Oct 12, 2026, 13:49 UTC)
- Influential citations0 (reference 3, via semantic-scholar, Oct 12, 2026, 13:49 UTC)
- Hugging Face upvotes27 (reference 25, via hf-daily, Oct 12, 2026, 13:49 UTC)
- GitHub stars281 (reference 250, via hf-daily, Oct 12, 2026, 13:49 UTC)