RSI-Anything: Unlocking Recursive Self-Improvement with World Models
Predict, then test: the policy and the world model go into the next round together, and only if each passes and the two still fit.
Move the cursor over the diagram
Overview
Cross-domain recursive self-improvement with world models
Built on JEPA-Anything: world-model predictions pick which candidates to test for real; feedback improves the policy or workflow, and the world model once its predictions prove unreliable; only updates that pass their checks are kept.
RSI-Anything is a method study of recursive self-improvement (RSI) that takes JEPA-Anything as its cross-domain predictive foundation.
Recursive self-improvement aims to turn what a system learns in one round of interaction into lasting improvements it still uses when it acts and learns in the next. Two things get in the way. External feedback is expensive: running tests or experiments costs something, so only a few candidates can be checked for real. And once the policy changes, so do the candidates it proposes, and a world model that predicted well before may no longer do so. Improving the policy and the world model separately does not guarantee that the pair works better together.
RSI-Anything uses world-model predictions to choose which candidates go out for external evaluation and which experience is used for learning. When real feedback comes back it improves the policy or the agent workflow, and the world model is adapted only when its predictions are judged unreliable and there is enough data and budget to do so. The two can update on their own schedules. Each new version first has to pass its own check, and the assembled pair is then compared with the current one under the same conditions; it is kept only if it meets criteria fixed in advance. The pair that is kept shapes which candidates the next round proposes and what experience it gathers, which is what makes the improvement recursive.
Where it is evaluated
- Code repair
- GUI interaction
- Laboratory planning
- Reaction optimization
- An end-to-end immune-science application
The technical report, the GitHub repository and the models on Hugging Face are public.
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.
Authors
Venue
Cite
BibTeX
@techreport{cui2026rsi,
title = {{RSI-Anything}: Unlocking Recursive Self-Improvement with World Models},
author = {Cui, Taoyong and Zeng, Pinxian and Xu, Wanghan and Xiao, Hao and Xue, Shuhan and Gao, Qiang and Ouyang, Wanli and Heng, Pheng Ann and Yin, Zhenfei and Wu, Yingcheng and Yang, Ling},
institution = {PhAI Labs},
type = {Technical Report},
number = {PHAI-TR-2026-05},
month = {October},
year = {2026},
url = {https://phai-labs.com/papers/rsi-anything/},
note = {Version v1}
}