RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Hugging Face Daily Papers Papers
recursive-self-improvement world-models jepa agentic-ai code-repair scientific-discovery self-supervised-learning

Summary

RSI-Anything 提出一个基于 JEPA-Anything 的领域通用递归自我改进框架，利用预测性世界模型指导行动与学习数据选择，在代码修复、GUI 任务、实验室规划和反应优化等多个领域均取得显著性能提升。

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.
Original Article
View Cached Full Text

Cached at: 10/12/26, 02:37 AM

Paper page - RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Source: https://huggingface.co/papers/2610.13912

Abstract

Recursiveself-improvement(RSI)aimstotransforminteractionexperienceintopersistentimprovements,yetexternalfeedbackiscostlyandworld-modelpredictionsmaybecomeunreliableaspoliciesevolve.WeintroduceRSI-Anything,adomain-generalframeworkbuiltonJEPA-Anythingthatusespredictiveworldmodelstoguideactionandlearning-dataselection.Observedfeedbackdrivespolicyorworkflowimprovementandconditionalworld-modeladaptation,whilecomponentandcompatibilitychecksgoverntheretentionofupdatedpolicy-modelpairs.Acrossdiversecomputationalandscientificdomains,RSI-Anythingdemonstratessubstantialgains.Incoderepair,withthecoderfixed,successincreasesfrom26.3%withastaticverifierto29.2%throughpredictiveselectionand31.2%afterworld-modeladaptation,atcomparabletestusage.Graphicaluserinterface(GUI)evaluationsshowedhighertaskcompletion,whileaverageactionsdecreaseby39.4%.Acrossfivesuccessivepolicyversions,laboratory-planningscoresmorethandoublefrom21.80%to46.01%.Inreactionoptimization,RSI-Anythingachieves96.15%meanbestobservedyieldversus82.16%forBayesianoptimizationunderthesame40-experimentbudget.Anend-to-endimmune-scienceapplicationfurtherconnectsworkflowevolutionandpredictivemodelingwiththerapeutichypothesisgeneration.Theseresultsdemonstratehowpredictiveworldmodelsandretainedsystemupdatesenablerecursiveimprovementacrossdiverseenvironments.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2610\.13912

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.13912 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.13912 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.13912 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Recursive Self-Improvement in Unified Multimodal Models

arXiv cs.CL

The paper proposes Recursive Self-Improvement (RSI), a training loop in which a unified multimodal model's text and visual abilities generate training data for each other, with program execution providing verified supervision. Evaluated on charts with a new BasicChartBench benchmark, four rounds of RSI improve performance from 45.7% to 60.2% while verified-program share rises from 48.9% to 95.2%.