The Frontier Must Grow - Self-proposed, interpreter-labelled training roughly doubles a 4B model's accuracy on a fresh exam as its verified frontier grows
Organizations: Swedish Embedded AB
Abstract
A model can learn from problems it poses itself when an executable oracle supplies the answers. Qwen3-4B proposed Lua 5.1 programs; those it predicted wrong at least once in four samples joined a pool labelled by the interpreter, each round adding twice as many programs as the last (300, 900, 2100 in total), and each round trained a fresh adapter from the base on the pool. On the original exam the procedure met its registered criterion, an item-level test of each adapter against its predecessor. On a 2340-item exam drawn afterwards, accuracy rose from 8.3% to 16.7%; that follow-up's registered criteria were not met because round 1 gained nothing, while rounds 2 and 3 added 5.0 and 2.9 points on average, both intervals above zero. One fit on the same amount of base-proposed frontier data reached 14.6%, so the rounds' 2.1-point advantage is inconclusive. Three earlier registered series met no per-lineage criterion, and the same loop showed no gain on repository tasks or for a 27B agent in those configurations.
Figures & tables
| Items right of 889 | Gen. 1 vs base | Gen. 2 vs gen. 1 | Gen. 3 vs gen. 2 | ||||||||
| Lineage | base | g1 | g2 | g3 | W/L | W/L | W/L | All hold | |||
| S3 | |||||||||||
| r0 | 0 | 58 | 122 | 123 | 58/0 | 78/14 | 29/28 | 0.5 | no | ||
| r1 | 0 | 72 | 101 | 91 | 72/0 | 41/12 | 18/28 | 0.948 | no | ||
| r2 | 0 | 67 | 86 | 121 | 67/0 | 38/19 | 0.00817 | 48/13 | yes | ||
| r3 | 0 | 91 | 118 | 142 | 91/0 | 42/15 | 0.00023 | 47/23 | 0.00279 | yes | |
| Model | Training records | Thinking | F answered (%) |
|---|---|---|---|
| Qwen3-4B base | – | off | 8.3 |
| S4 generation 1 | 300, own frontier | off | 8.7 |
| S4 generation 2 | 900, own frontier | off | 13.8 |
| S4 generation 3 | 2100, own frontier | off | 16.7 |
| same data, new seed | 2100, own frontier | off | 16.9 |
| M-900 (one fit) | 900, base frontier | off | 12.4 |
| Test | What it trained on | Registered criterion | Outcome |
|---|---|---|---|
| S1 A | own tasks, closed-book loop | gen. 3 beats gen. 2 | not met; gains were protocol adaptation [RS11,RS42] |
| S1 B | A without starving proposals | gen. 2 and 3 each improve | not met [RS42] |
| S1 H | own programs, interpreter labels | pooled steps, no replicate falls | met (pooled) [RS12] |
| S1 HP | H in Python | as H | not met at gen. 3 [RS13] |
| S1 HR | HP with replay and pooled retention | as H | met (pooled), each step’s gain from one replicate [RS14] |
| S1 R | own verified reasoning | monotone gain on unseen families | not met [RS15] |
Appendix figures & tables16 assets
Supplementary material from the paper’s appendix.
Appendix
| Run | Base | Tokens | Peak MiB | Seconds | Outcome |
|---|---|---|---|---|---|
| probe, 64 layers, random init | NF4 | 8192 | 35947 | 404.74 | step done |
| probe, 64 layers, random init | bf16 | 8192 | 67011 | 435.47 | step done |
| probe, 64 layers, random init | bf16 | 16384 | 77879 | 873.64 | step done |
| 27B, 1 step | NF4 | 1024 | 27989 | 460.4 | finished |
| 27B, 1 step | bf16 | 1024 | 59053 | 321.1 | finished |
| 27B, 40 steps | NF4 | 256 | 24559 | 936.8 | finished |
| Non-tied | Wins needed | Smallest | Power if | ||
|---|---|---|---|---|---|
| families | for | (all wins) | 0.7 | 0.8 | 0.9 |
| 4 | none | 0.062 | 0.00 | 0.00 | 0.00 |
| 5 | 5 | 0.031 | 0.17 | 0.33 | 0.59 |
| 6 | 6 | 0.016 | 0.12 | 0.26 | 0.53 |
| 8 | 7 | 0.0039 | 0.26 | 0.50 | 0.81 |
| 10 | 9 | 0.00098 | 0.15 | 0.38 | 0.74 |
| Exp. | Repository | Arm | Families | Wins | Losses | Status | |
|---|---|---|---|---|---|---|---|
| CE4 | eight repositories (pilot subset S1) | adapter against untrained 8B | 21 | 0 | 1 | 1.000 | PILOT |
| CE8 | eight repositories (pilot subset S1) | CE8-T against the 27B base | 13 | 3 | 4 | 0.773 | PILOT |
| CE8 | eight repositories (pilot subset S1) | CE8-T-S (shuffled control) against the 27B base | 16 | 2 | 6 | 0.965 | PILOT |
| CE8 | eight repositories (pilot subset S1) | CE8-T-u1b (decision-level) against the 27B base | 13 | 1 | 4 | 0.969 | PILOT |
| Set | Tasks | Success | Stopped | Hidden pass | Audit removed | Passed clean | Failed |
|---|---|---|---|---|---|---|---|
| caldate p1 | 25 | 13 | 12 | 13 | 7 | 6 | 19 |
| exprcalc p1 | 56 | 13 | 43 | 10 | 7 | 3 | 53 |
| graphkit p1 | 51 | 27 | 24 | 24 | 13 | 11 | 40 |
| iniparse p1 | 61 | 21 | 40 | 18 | 7 | 11 | 50 |
| linediff p1 | 50 | 21 | 29 | 18 | 7 | 11 | 39 |
| mdrender p1 | 43 | 19 | 24 | 13 | 4 | 9 | 34 |
| Probe | Arm | Families | Wins | Losses | Status | |
|---|---|---|---|---|---|---|
| D46-SS | decisive actions against all actions (seed 13) | 42 | 16 | 1 | 0.000137 | PILOT |
| D46-SS | decisive actions against all actions (seed 1) | 38 | 8 | 4 | 0.194 | PILOT |
| D46-SS | all actions against the base (seed 13) | 35 | 4 | 11 | 0.982 | PILOT |
| D46-RCV | 6 steps from win1 against the base | 36 | 4 | 6 | 0.828 | PILOT |
| D46-RCV | 18 steps from win1 against the base | 34 | 6 | 8 | 0.788 | PILOT |
| D46-RCV | 36 steps from win1 against the base | 31 | 10 | 5 | 0.151 | PILOT |
| Model (optimizer state) | Card (GiB) | Host (GiB) | s / 8 steps | Loss |
|---|---|---|---|---|
| Qwen3-0.6B (fp32) | 7.8 | 10.9 | 62 | 1.38 0.91 |
| Qwen3-1.7B (fp32) | 15.9 | 32.6 | 128 | 1.56 0.81 |
| Qwen3-4B (fp32) | 33.6 | 75.2 | 251 | 1.76 0.91 |
| Qwen3-8B (fp32) | 65.6 | 152.7 | 488 | 1.12 0.47 |
| Qwen3-8B (int8 moments) | 65.7 | 107.5 | 459 | 1.30 0.83 |
| Family | Language | Tests | Admitted tasks |
|---|---|---|---|
| iniparse | python | 279 | 177 |
| ttlcache | python | 257 | 159 |
| exprcalc | python | 256 | 186 |
| linediff | python | 278 | 152 |
| mdrender | python | 270 | 148 |
| caldate | lua | 250 | 132 |
| Date | Change | Before |
|---|---|---|
| 10-21 | CE8-T’s memorisation guard judges the kept checkpoint: memorised if its monitoring loss is not below the base’s, or its windowed training loss is below half its monitoring loss. Defined after the original guard stopped both CE8 runs on a last-evaluation rise of 0.0003 to 0.003; Under this rule both CE8 runs would pass (kept checkpoints at steps 27 and 30, monitoring loss below the base’s, training loss above half of it); CE8 stays not evaluated, because the guard in force for it fired. From here on the protocol changes in this paper, not in the registration file. | CE8-T’s training |
| 10-21 | CE8 being closed, CE8-T gets its own shuffled negative control (CE8-T-S, from the CE8-T experiences) and the one-pass budget the second CE8 run used; its step count follows the trainer’s own record count, read from a one-step sizing run. | CE8-T’s training |
| 10-22 | G8 for the 27B compares served and in-process teacher-forced log-probabilities on held-out records, against the base’s own served-vs-in-process gap, instead of agent verdicts: the 27B has no in-process agent path (splinter’s local provider runs qwen3 only), found when the served half of the verdict check had run (9 of 23 verified) and before any comparison of the two halves existed. | G8 and any evaluation arm |
| 10-22 | CE8-T and CE8-T-S are solved on the pilot subset P23 under amendment 20 (thinking off) before G8 is measured, which the registration places before any arm; both comparisons have fewer than 25 non-tied families, are labelled pilots by the rule, and no confirmatory query follows from them. | any CE8-T evaluation |
| Date | Change | Before |
|---|---|---|
| 10-25 | The release gate’s improvement check also requires the candidate to have solved at least as many of the suite’s assigned tasks as its champion; an attempt withheld as exposed or as a harness failure counts as a task that arm did not solve, so a regression can no longer leave the paired test’s denominator. The measured shape that motivated it: a base at 21/46 (9 exposed) against a candidate at 15/46 (19 exposed) read as 5W-3L-15T under the paired test alone. | any release after it |
| 10-25 | Development probes on D46 (46 tasks, one per family, greedy) measure the supervision ablation and the recovery dose-response. They are labelled pilots, are not the registered confirmatory query, and their outcomes are not used as evidence for it; the registration, its partitions and its denominators are unchanged. [D46A,D46C,RCVA,RCVC] | the D46 probes |
| 10-25 | The evaluation-variance explanation is corrected. The two serving probes that appeared to reproduce run-to-run nondeterminism hashed the whole response payload, which carries a random tool-call id and a random chat id, so their distinct-completion counts were artifacts. Remeasured on the completion’s token ids and log-probabilities, a batch-1 greedy decode is bit-reproducible, a cache hit equals a cold prefill, and the co-batch does change a row (the int8 projections switch to a tensor-core block from five rows and the decode attention sizes its split count from the batch) - but one request in flight does not make a whole episode reproducible, so a second, unidentified source remains. The three-run greedy spread this paragraph explains (30, 31 and 26 of 46) is unchanged. [REP1,REP2] | the REP1 paragraph and any reading of a single greedy arm |
| 10-25 | The confirmatory candidate is registered before its query: the decisive-action adapter of training seed 13 (corpus blake3:92252209 , rank 16, alpha 32, , 120 steps, packed-bf16 base, the rebuilt training binary), chosen after the six-decoding-seed development read on D46 in which it won 22 families, lost 11 and tied 13 against the base and the same against its all-action control (p=0.0401 each) while the two controls did not separate. The query solves the frozen qualification set ( blake3:f7fe502f , 46 families) with the candidate, its base and the all-action control at the three registered decoding seeds and the protocol’s sampling; the decision is the registered one-sided exact sign test at , and a result that is not significant is reported as not shown. [PROTO6] | any candidate query |
| Date | Change | Before |
|---|---|---|
| 10-26 | The registration’s amendment history (the dated amendments appended to prereg/coding-tasks.md before the runs they could affect) is kept in the repository’s history of that file and is no longer restated in this paper; the protocol of Appendix M is the registration as it stands, and the changes made in this paper are the rows above. | the paper’s final form |
| 11-06 | Generation 0 of the 27B loop ( Appendix O ) is decided without the mechanical-design exam (its trials of up to three hours could not finish in the lease at the scaled load) and on the pooled exam trials: a disk-quota failure and one overloaded re-run ended part of the original exam jobs, so each candidate is paired with the champion over every trial of the exam and its re-runs that the agent itself ended, leaving out trials ended by an infrastructure exception, a model-server error or a step timeout (the original candidate exams ran overloaded). | generation 0’s decision |
| 11-07 | Generation 1 explores a frontier pool, the training tasks generation 0 did not always solve and the never-explored training tasks with several faults, with the promoted champion; its exploration is stopped at a fixed time (04:30) to leave the lease room for a second decision, which gave each pool task 3 or 4 attempts instead of the planned 8, and two of the four planned training variants are trained. | generation 1’s training |
| 11-07 | No third generation was run (it could not finish in the lease). Instead the base sat the held-out exams on generation 1’s stack, the repository exam with several faults completed by a second job on the idle cards, so that the base and both champions are compared on one measurement. | the comparison of the base with both champions |
| Series | Change | Before |
|---|---|---|
| S1 HL | The first run of arm HL ended on the project disk’s inode quota and was not evaluated; the registered replication was rerun on a cleared disk with the same scripts and binaries. [RS16,RS37] | arm HL’s evaluation |
| S2 | The policy-gradient objective scores the behaviour policy as the start of the arm, because the records carry no sampler log-probabilities at the launch build; each arm samples fresh from the policy it starts from. Generation 2 was not run (the shared adapter card id); the criterion was already decided by generation 1. [RS08,RS37] | generation 1 |
| S3 | Lineage r2 was relaunched before its first round with the request cap of its held-out proposals raised to 1400 (its seed reached 415 of 450 programs in 700 requests); r3’s generation 3 was resumed from its journals after a transient connection close, with the same build and settings. [RS37] | r2’s first round; r3’s verdict |
| S4 | The examiner’s build was changed so that it identifies a declared base by the checkpoint’s content under either digest rule, and it served on another card; exam, protocol, serving build, tier, candidates and criterion unchanged. [RS06,RS37] | any verdict |
Language Model Self-Improvement
Language model self-improvement studies how models use their own outputs, feedback, and experience to improve with less external supervision.
See all 194 papers