cs.AIOct 7, 2026
SaveRSI-Forge: From Research Papers to Environments for Recursive Self-Improvement
Organizations: Scale AI · University of California, Santa Cruz · University of North Carolina at Chapel Hill
Abstract
Environments are the foundation of recursive self-improvement: they provide the problems agents work on and the feedback used to evaluate progress. Yet constructing challenging research environments with reliable evaluation still depends on domain experts, limiting their scale and disciplinary coverage. We introduce RSI-Forge, a multi-agent pipeline that turns published papers into executable environments for self-improvement. Three agents coordinate construction, reproduction, and review to produce tasks with automated evaluators; each paper's method is independently reimplemented to establish a baseline score. We present 210 environments across 18 fields, including 90 reviewed by independent human domain experts. Both experts and agent judges give high ratings to the potential for improving the provided starting solutions and the evaluators' ability to distinguish solution quality, whereas experts are more critical of shortcut resistance, faithfulness to the source paper, and whether a single idea can exhaust a task. To validate their use for repeated improvement, we evaluate four models over 3 successive attempts on 120 environments, with each attempt inheriting prior code and notes while model weights remain fixed. At least one model improves after the first attempt in 84% of environments. Models also outperform the reproduced paper methods in 68 of the 120 environments, demonstrating room for gains beyond these baselines. Transcript analysis identifies work beyond parameter tuning in 95% of these successful attempts. Analysis of the resulting trajectories shows that models scoring lower on these tasks explore less, more often accept gains smaller than the reported standard error, and rely more heavily on tuning to the development set. RSI-Forge provides a scalable approach to constructing research environments for training and evaluating self-improving agents.
Figures & tables
Figure 1 : Overview of RSI-Forge and the information available to each agent. Failed checks lead to repair or rejection before an environment is accepted. The output count includes all 210 environments. The performance bars report median scores of final solutions after 3 successive attempts on 120 environments sampled from the main construction run. Scores are normalized so that the starting solution is 0 and the target score is 1 ( Eq. 1 ).
| Stage | Count |
| Source papers screened | 10,800 |
| Papers eligible for construction | 2,117 |
| Construction attempts begun | 213 |
| Passed Design | 199 |
| Passed Build | 198 |
| Passed Independent Reproduction | 189 |
Table 1: Main-run construction funnel. Counts include environments that passed after repairs. The additional 30 environments built with GPT-5.6-sol are outside this funnel.
| Field | Task | Evaluation objective |
|---|---|---|
| Robotics | Choose footholds on a terrain map | Increase distance in six steps |
| Life Sciences | Propose molecules for a binding pocket | Improve docking scores |
| Earth, Climate & Space | Estimate weather from partial observations | Reduce state-estimation error |
| Statistics & Inference | Estimate effects without a control series | Reduce treatment-effect error |
| Software Engineering & Formal Methods | Generate tests within a fixed budget | Trigger more distinct failures |
| Computational Physics | Infer a plasma boundary from magnetic data | Reduce boundary-estimation error |
Table 2: Examples of environments from the main construction run.
| Issue identified | Share of repair passages |
|---|---|
| Checks unable to detect the intended failure | 66% |
| Incorrect or incomplete instructions | 63% |
| Checks inspecting a different copy of the code | 54% |
| Score gains without performing the intended work | 37% |
Table 3: Most common construction defects identified by model-based coding of repair passages. Percentages are shares of repair passages; categories overlap.
Figure 2 : Quality ratings from human experts and agent judges on the same 90 environments, with one expert and three judges per environment. Points show means on a 1–5 scale (higher is better). Agent ratings are averaged within environments; rows are ordered by expert mean. Only experts received available solver results. Sections B.2.2 and 6 give the rubric and per-dimension standard deviations.
| Median normalized score | Session 3 | ||||
|---|---|---|---|---|---|
| Model | Session 1 | Session 2 | Session 3 | 95% CI | Mean rank |
| Claude Opus 5 | 0.754 | 0.791 | 0.800 | [0.753, 0.867] | 1.67 |
| GPT-5.6-sol | 0.673 | 0.747 | 0.761 | [0.723, 0.824] | 1.73 |
| DeepSeek-V4-Flash | 0.550 | 0.594 | 0.647 | [0.586, 0.711] | 2.97 |
| Claude Haiku 4.5 | 0.129 | 0.277 | 0.332 | [0.203, 0.451] | 3.63 |
Table 4: Submitted-solution scores on 120 environments, normalized to the starting solution (0) and target (1). Session 3 confidence intervals use bootstrap resampling of environments. Mean rank averages within-environment ranks at session 3 (1 is best).
Figure 3 : Transcript-coded behavior across 360 sessions per model (120 environments, three sessions each). Cell values and color intensity show percentages of sessions assigned to each group by model-based open coding. Groups overlap; “improvement” covers developing and checking solutions, without requiring score gains.
Figure 4 : A three-session Claude Opus 5 chain on a foothold-selection task. Open points are saved solutions graded on the held-out test set; filled points mark final submissions, with normalized scores of 0.15, 0.33, and 0.58. The annotations summarize the changes recorded in each session. The third session adds a ground-support check and reverses the second session’s averaging rule.
Appendix figures & tables10 assets
Supplementary material from the paper’s appendix.
Appendix
| Field | Count | Field | Count |
|---|---|---|---|
| Robotics | 14 | Security & Cryptography | 10 |
| Life Sciences | 13 | Neuroscience | 9 |
| Earth, Climate & Space | 13 | Optimisation & Discrete Algorithms | 9 |
| Statistics & Inference | 13 | Chemistry & Materials | 9 |
| Networks & Information Th. | 12 | Graphics & Rendering | 8 |
| Software Eng. & Formal Methods | 12 | Quantitative Finance | 7 |
Table 5: Field composition of the 180 main-run environments.
| Dimension | Experts | SD | Panel | SD | Gap |
|---|---|---|---|---|---|
| Research problem | 4.39 | 0.84 | 4.59 | 0.32 | |
| Room above starting solution | 4.81 | 0.51 | 4.89 | 0.31 | |
| Resistance to saturation | 3.09 | 0.96 | 3.98 | 0.84 | |
| Faithfulness to source paper | 3.72 | 0.87 | 4.22 | 0.51 | |
| Metric validity | 4.40 | 0.85 | 4.49 | 0.45 | |
| Single objective | 4.61 | 0.90 | 4.66 | 0.46 |
Table 6: Human-expert and agent-panel ratings on the same 90 environments. Scores are means on a 1–5 scale; SD denotes standard deviation. Agent ratings are averaged within environments; Gap is the panel mean minus the expert mean.
| Dimension | RSI-Exam | RSI-Forge | Gap |
|---|---|---|---|
| Score discrimination | 2.64 | 4.65 | |
| Development–test distinction | 3.23 | 4.67 | |
| Shortcut resistance | 3.92 | 4.67 | |
| Single objective | 4.64 | 4.66 | |
| Room above starting solution | 4.87 | 4.89 | |
| Research problem | 4.61 | 4.59 |
Table 7: Ratings from the same three agent judges on 34 manually constructed RSI-Exam tasks and the 90 RSI-Forge environments in Table 6 . Gap is RSI-Forge minus RSI-Exam; the 8 dimensions exclude faithfulness because this comparison has no common source-paper reference. The task sets are unpaired, so the differences do not isolate the effect of automated construction.
| Axis | A score of 1 | A score of 3 | A score of 5 |
|---|---|---|---|
| Real problem | a toy with no research content | a real problem, narrowly posed | you would be pleased to see a student work on this |
| Headroom | the starter is already near the ceiling | a competent effort gains something | clearly large, and you can name where it comes from |
| Not saturable | one change takes most of the range | the first change is worth it, more remains | improvement requires several independent ideas |
| Faithful to the paper | unrelated to what the paper does | related, but the hard part has been removed | this is the paper’s problem, honestly posed |
| Metric validity | measures something else | a reasonable proxy | this is the quantity the field would report |
| Single direction | two objectives silently traded | one quantity, the constraint is loose | one quantity, one direction, the constraint binds |
Table 8 : Descriptions of scores 1, 3, and 5 in the environment-quality rubric, reproduced verbatim. The dimensions are grouped here as in the rating summaries; the human review form presents faithfulness to the source paper last.
| Versions graded | Output tokens (thousands) | |||
|---|---|---|---|---|
| Model | Median | Mean | Median | Mean |
| Claude Opus 5 | 4.0 | 69.3 | ||
| GPT-5.6-sol | 2.0 | 22.1 | ||
| DeepSeek-V4-Flash | 2.0 | 54.5 | ||
| Claude Haiku 4.5 | 2.0 | 30.2 | ||
Table 9: Activity per session on the 120 main evaluation environments. Versions are saved runnable solutions that were graded; output tokens are in thousands. Means include one standard deviation. Token volume is not equivalent to monetary or computational cost across providers.
Figure 5 : Transcript-coded mechanisms as percentages of each model’s sessions that surpass the reproduced baseline. The codebook was derived from a sample and fixed before counting. Sessions may receive several labels; nine categories cover work beyond parameter tuning. The labels describe work within the constructed task and do not establish scientific novelty.
Figure 6 : Open-coded families grouped as improvement (21), exploration (27), and shortcuts (14). Cells show percentages of each model’s 360 sessions assigned a family. Labels overlap. Shading is scaled within each group; printed percentages support comparisons across groups. The ungrouped family for submitting the inherited solution unchanged is omitted.
| Group | Practice | Required evidence |
|---|---|---|
| Improvement | Check inherited results | Before any edit, rerun the inherited solution to reproduce its recorded score or independently derive its central claim. |
| Use the task specification | Justify the submitted change from a task-document fact or metric property; a parameter-sweep result alone is insufficient. | |
| Improve robustness | Address failures such as degenerate inputs, timing limits, or fallback behavior without targeting the metric. | |
| Exploration | Bound potential improvement | Before searching, compute an upper or lower performance bound and decompose the remaining gap to allocate the budget. |
| Test beyond development data | Evaluate a change beyond the supplied development instances using a stress test or test of invariance. | |
| Compare with error bars | Use an explicit error bar when accepting or rejecting a change; a before-and-after comparison alone is insufficient. |
Table 10: The ten fixed practices, distinct from the open-coded families in Fig. 6 and the successful-session mechanisms in Fig. 5 . Labels and operational criteria are paraphrased from the coding scheme; timing requirements and exclusions are retained.
| Claude Opus 5 | GPT-5.6-sol | |||
|---|---|---|---|---|
| Agent judge | Mean | Mean | ||
| Claude Opus 5 (Claude Code) | 4.37 | 180 | 4.25 | 30 |
| GPT-5.6-sol (Codex) | 4.40 | 180 | 4.27 | 30 |
| Gemini 3.7 Flash (Claude Code) | 4.88 | 180 | 4.74 | 30 |
Table 11: Agent-judge ratings by construction backend. Cells average over rubric dimensions, then environments; counts rated environments. For this comparison, Gemini 3.7 Flash uses Claude Code; Section B.2 compares its ratings under Claude Code and Antigravity.
| Claude Opus 5 | GPT-5.6-sol | |||
|---|---|---|---|---|
| Solver model | Median | Median | ||
| Claude Opus 5 | 0.800 | 120 | 0.784 | 30 |
| GPT-5.6-sol | 0.761 | 120 | 0.736 | 30 |
| DeepSeek-V4-Flash | 0.647 | 120 | 0.564 | 30 |
| Claude Haiku 4.5 | 0.332 | 120 | 0.363 | 30 |
Table 12: Median final submitted normalized scores after three sessions by construction backend. The main-backend column repeats session 3 of Table 4 ; counts chains with all three sessions scored. Construction sets are unpaired.