cs.CLOct 9, 2026
SaveRSI-Anything: Unlocking Recursive Self-Improvement with World Models
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.
Figures & tables
Figure 1: RSI-Anything overview. Building on the cross-domain predictive foundation of JEPA-Anything, RSI-Anything uses world-model predictions to support understanding, planning, and action selection across diverse tasks. Interaction feedback drives policy or workflow updates and conditional world-model adaptation. Component and compatibility checks determine which policy–model pair is retained to guide the next round of interaction and learning, closing the recursive self-improvement loop.
Figure 2: RSI-Anything couples prediction-guided action with retained system updates. a , Building on JEPA-Anything, world-model predictions guide candidate selection for external evaluation. Only the executed candidate (B) yields paired prediction–observation feedback. Feedback supports policy or workflow revision and reliability assessment; world-model adaptation depends on prediction reliability, available data, and budget. Component and compatibility checks determine the retained policy–model pair, which shapes candidates and learning experiences in the next round. b , The shared mechanism is instantiated in code repair, GUI interaction, laboratory planning, and reaction optimization. An end-to-end immune-science application connects workflow evolution, immune world-model construction, analysis with self-correction, and prospective hypothesis generation.
| Object | Change rule | Carried forward |
|---|---|---|
| Task and evaluation specification | Fixed for the run | Task objectives and definitions, interfaces, evaluation criteria, constraints, budget limits, and acceptance and stopping rules |
| Task state and experience | Actions and observations revise the state and extend prediction–observation records | Current task state for subsequent actions; accumulated records for selection and learning |
| Policy configuration | Feedback-driven policy learning or workflow revision proposes a candidate version; component and pair checks govern acceptance | Accepted policy configuration; otherwise the current version |
| World model | Prediction unreliability, sufficient data and budget trigger an adaptation attempt; component and pair checks govern acceptance | Accepted predictor; otherwise the current version |
Table 1: Fixed settings, update rules, and retained state in a recursive run.
Figure 3: Prediction-guided selection and world-model adaptation in code repair. a , Illustrative repair of a non-convergent loop, from candidate patches and predicted outcomes to execution and test feedback. A–C depict example patches; the benchmark uses a fixed coder and four candidates per round. Feedback supports predictor updates in the adaptive configuration. Panels b–d report results on 200 CodeContests tasks across three seeds with up to three feedback rounds. b , Final hidden-test all-pass rate. c , Candidate-ranking accuracy and five-class Brier score for the static verifier and the fixed-world-model configuration. Higher ranking accuracy and lower Brier score indicate better predictive performance. d , Mean online test-suite calls per task. e,f , Final full-test success averaged over three seeds on APPS Introductory (1,000 problems) and LiveCodeBench v6 (1,055 problems), respectively. Fixed WM denotes RSI-Anything with a fixed world model (CURE-WM-Lite); Adaptive WM denotes RSI-Anything with world-model adaptation. Green shades identify world-model-based methods; gray shades identify baselines.
| Selection method | Hidden all-pass | Online calls/task |
|---|---|---|
| Random-K | 26.0% | 3.72 |
| Capacity-matched static verifier | 26.3% | 3.72 |
| RSI-Anything with a fixed world model (CURE-WM-Lite) | 29.2% | 3.71 |
| RSI-Anything with world-model adaptation | 31.2% | 3.72 |
Table 2: Three-round repair on CodeContests Li et al. (2022) under a shared coder and candidate budget. Both RSI-Anything configurations use world-model-guided candidate selection: one keeps the world model fixed (CURE-WM-Lite), and the other additionally adapts it using feedback.
Figure 4: Task completion and action behavior in GUI environments. a,b , Illustrative MiniWoB++ checkbox selection and OSWorld spreadsheet completion tasks, showing initial and target states. c , MiniWoB++ click-checkboxes success across baseline, adapted, and final configurations for RSI-Anything and the World-based control. d , OSWorld success-rate gains relative to the initial agent. The annotation gives the additional relative gain of RSI-Anything over RLAnything; all gains are relative percentages. e–g , Mean actions per episode, repeated-click count, and number of episodes with incorrect submissions, respectively, for the RSI-Anything configurations in c . Lines connect evaluated configurations.
Figure 5: Successive policy improvement with RSI-Anything on the 200-task LabHorizon F200 Level-2 benchmark Stanford Cong Lab (2026) . a , Illustrative planning workflow connecting protocol context, a 4B policy, predictive evaluation of action sequences and parameters, an execution plan, and assessment. Dashed feedback paths depict update routes in the framework; the quantitative comparison below follows retained policy versions. b , Five consecutive versions of the same 4B policy from one self-improvement process. c , Final Score for each version, combining action-sequence similarity and parameter accuracy. The dashed line marks the Actor–Simulator–Selector reference at . Versions are ordered by development sequence; spacing is schematic.
| System | L1 Acc. | L2 Final |
|---|---|---|
| Grok 4.3 xAI (2026) | 0.555 | 0.3244 |
| Gemini 3.1 Pro Google (2026) | 0.465 | 0.3263 |
| GPT-5.5 OpenAI (2026) | 0.535 | 0.2276 |
| Kimi K2.6 Moonshot AI (2026) | 0.550 | 0.3150 |
| Qwen3.6-35B-A3B Qwen Team (2026) , direct | 0.475 | 0.2534 |
| Qwen3.6-35B-A3B, trained | 0.635 | 0.4100 |
Table 3: LabHorizon benchmark scores for reference systems Stanford Cong Lab (2026) and RSI-Anything.
Figure 6: Reaction-condition optimization with RSI-Anything (green) and Bayesian optimization (gray). a , Illustrative GC-screen workflow connecting the reaction setup, catalyst/base/solvent options, prediction-guided condition selection, and measured yield. The reaction couples 4-chloroanisole and 4-(trifluoromethyl)phenylboronic acid using a Pd–NHC–DMS precatalyst. b , Best observed GC yield versus cumulative experiment count. c , GC yield after 20 experiments: for RSI-Anything and for Bayesian optimization. d , Illustrative flow-screen workflow for substrates 1c and 2b, with Pd(OAc) 2 , ligand, base, and solvent selection followed by LC–MS analysis. e , Mean best observed yield versus cumulative experiment count in the flow LC–MS screen. f , Yield after 40 experiments: and , respectively. Brackets indicate gains of and percentage points within the corresponding screen. Condition examples and feedback arrows illustrate the framework; curves and bars report the two separate screens.
Figure 7: An end-to-end application of RSI-Anything in immune science. A , evolution of scientific-agent workflows, construction of the immune world model, and model-guided analysis. B , action-conditioned transitions over structured cellular, tissue, and individual immune states, with readouts for interpretation, ranking, and hypothesis generation. Panels A and B adapted from Figure 1 of Cui et al. (2026a) .
| Setting | State; action | World model; prediction | Policy / workflow; feedback-driven changes | Feedback; evaluation |
|---|---|---|---|---|
| Code repair | Program, tests, and feedback; candidate revision | JEPA-Anything-based W1 adapted from Qwen2.5-Coder-3B-Instruct Hui et al. (2024) with LoRA Hu et al. (2022) ; five-class probabilities | Fixed ReasonFlux-Coder-7B; fixed or feedback-adapted W1 | Execution-test feedback; final test-suite success and online test usage |
| GUI interaction | Interface state and task; GUI action | GUI outcome predictor; consequences of candidate interface actions | Action policy and world model updated through interaction feedback | Task outcomes; completion and action-level diagnostics |
| Lab planning | Protocol context; candidate action sequence | JEPA-Anything-based protocol model; predicted consequences of a candidate sequence | 4B planning policy; five consecutive versions in one improvement process | Development feedback; L1 next-action accuracy and F200 L2 Final Score |
| Chemistry | Reaction; condition vector | ReactionT5–JEPA-Anything; yield distribution | Measured yields guide subsequent condition choices | Measured GC/LC–MS yields; best observed yield at matched experiment counts |
| Immune science | Cellular, tissue, and individual context; intervention | Immune world model Cui et al. (2026a) ; multiscale transition and biological readouts | Workflow evolution and world-model construction; fixed predictor during downstream analysis | Measured perturbations support development; withheld contexts assess forecasting |
Table 4: Domain bindings and reported update scope. The world model predicts consequences; the policy proposes or selects actions.