arXiv cs.CL· Taoyong Cui, Pinxian Zeng, Wanghan Xu, Hao Xiao, Shuhan Xue, Qiang Gao, Wanli Ouyang, Pheng Ann Heng, Zhenfei Yin, Yingcheng Wu, Ling Yang·· 6 天前AI 评分57
RSI-Anything：用世界模型实现递归自我改进的通用框架
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
AI 导读
论文提出 RSI-Anything，一个基于 JEPA-Anything 的领域通用框架，用预测式世界模型指导动作与学习数据选择，并通过组件与兼容性检查决定是否保留更新后的策略-模型对。
正文 · 原文
Authors:Taoyong Cui, Pinxian Zeng, Wanghan Xu, Hao Xiao, Shuhan Xue, Qiang Gao, Wanli Ouyang, Pheng Ann Heng, Zhenfei Yin, Yingcheng Wu, Ling Yang
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.
| Comments: | Code: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.13912 [cs.CL] |
| (or arXiv:2610.13912v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13912 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ling Yang [view email]
[v1]
Fri, 9 Oct 2026 17:50:30 UTC (9,225 KB)
来源：arXiv cs.CL · arxiv.org