RSI-Anything
A general-purpose recursive self-improvement framework built on JEPA-Anything. It uses a predictive world model to guide action selection and training data filtering, introduces a retention mechanism to ensure sustainable improvement, and supports task domains including code repair, GUI operation, and scientific planning.
Timeline (last 90 days)
RSI-Anything proposes a contrastive "propose-probe-compose" loop that improves code repair and GUI performance while providing PAC-style generalization guarantees.
RSI-Anything uses a predictive world model to guide the selection of actions and which data to use for learning
RSI-Anything introduces a retention mechanism with component checks and compatibility checks to decide whether an updated policy-model pair is worth retaining
In code repair tasks, the success rate using a static validator was 26.3%, rising to 29.2% after introducing predictive selection, and reaching 31.2% after world model adaptation
In GUI task evaluation, RSI-Anything reduced the average number of operation steps by 39.4%
RSI-Anything is a general framework proposed to address two pain points of recursive self-improvement (expensive external feedback and world model misalignment caused by policy evolution), built on top of JEPA-Anything
In reaction optimization tasks, RSI-Anything achieved an average best-observed yield of 96.15% under a budget of 40 experiments, outperforming Bayesian optimization's 82.16%
The RSI-Anything study presents an end-to-end immunological science application case that chains workflow evolution, predictive modeling, and therapeutic hypothesis generation
The retention mechanism implementation path of RSI-Anything is closer to system-level component validation than to parameter-level regularization constraints (such as EWC or PNN)
In the code repair experiments, the encoder (coder) was kept fixed, and the improvements were achieved under comparable test resource consumption
1 more timeline events
All Facts (11)
RSI-Anything proposes a contrastive "propose-probe-compose" loop that improves code repair and GUI performance while providing PAC-style generalization guarantees.
50%UnverifiedRSI-Anything uses a predictive world model to guide the selection of actions and which data to use for learning
50%UnverifiedRSI-Anything introduces a retention mechanism with component checks and compatibility checks to decide whether an updated policy-model pair is worth retaining
50%UnverifiedIn code repair tasks, the success rate using a static validator was 26.3%, rising to 29.2% after introducing predictive selection, and reaching 31.2% after world model adaptation
50%UnverifiedIn GUI task evaluation, RSI-Anything reduced the average number of operation steps by 39.4%
50%UnverifiedRSI-Anything is a general framework proposed to address two pain points of recursive self-improvement (expensive external feedback and world model misalignment caused by policy evolution), built on top of JEPA-Anything
50%UnverifiedIn reaction optimization tasks, RSI-Anything achieved an average best-observed yield of 96.15% under a budget of 40 experiments, outperforming Bayesian optimization's 82.16%
50%UnverifiedThe RSI-Anything study presents an end-to-end immunological science application case that chains workflow evolution, predictive modeling, and therapeutic hypothesis generation
50%UnverifiedThe retention mechanism implementation path of RSI-Anything is closer to system-level component validation than to parameter-level regularization constraints (such as EWC or PNN)
50%UnverifiedIn the code repair experiments, the encoder (coder) was kept fixed, and the improvements were achieved under comparable test resource consumption
50%UnverifiedAcross five consecutive policy version iterations, the laboratory planning score improved from 21.80% to 46.01%
50%