Search papers, labs, and topics across Lattice.
RSI-Anything leverages JEPA-Anything's predictive world models to guide action and learning-data selection, enabling recursive self-improvement by adapting world models conditionally and retaining updated policy-model pairs through component and compatibility checks. This domain-general framework demonstrates significant performance gains across code repair, GUI interaction, laboratory planning, and reaction optimization by effectively transforming interaction experience into persistent improvements. Notably, in laboratory planning, successive policy versions more than double scores, and in reaction optimization, it surpasses Bayesian optimization within a fixed budget.
Predictive world models, not just static feedback, unlock substantial gains in recursive self-improvement across diverse domains, from code to scientific discovery.
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.
