Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning
Organizations: PRISM AI Safety Research
Abstract
Formal world models can support planning, verification, and safety reasoning, but constructing them from open-ended natural-language situations is difficult, particularly in multi-agent settings where several formalizations may be plausible. We study whether five LLMs can generate such world models as partially observable stochastic games and whether mechanical validity is sufficient to establish that the resulting model faithfully represents the intended decision problem. We introduce a benchmark of 44 scenarios spanning game, situational, and cultural settings and evaluate generated world models along three dimensions: mechanical validity, reference-relative structural agreement, and semantic criteria. Across three empirical tracks, we analyze 410 first-pass generations. In the reference-backed game track, 134/135 generated world models pass a strict mechanical audit, yet mean permutation-invariant structural F1 is only 0.366, with just 28/134 mechanically valid models exactly matching the authored reference. In the cultural track, explicitly naming the country changes the generated structural representation for most LLMs while producing only small changes in automated semantic scores. These results show that executability is a necessary but insufficient criterion for LLM-generated world models: models that are mechanically valid can still differ substantially in the structure used by downstream neuro-symbolic reasoning and planning.
Figures & tables
| Track | Lane 1: mechanical | Lane 2a: structural | Lane 3: semantic |
|---|---|---|---|
| Game | 134/135 post-hoc | mean F1 .3660 ∗ | checklist 135/135 † |
| Situational | 104/135 | mean F1 .4324 ∗ | checklist 105/135 † |
| Cultural | 125/140 | mean F1 .5533 | checklist 136/140; mean .8963 † |
| LLM | Coverage | Precision | Mean F1 | Median [Q1,Q3] | Exact |
|---|---|---|---|---|---|
| Claude Opus 5 | .3133 | .1416 | .1709 | .1128 [.0597,.2312] | 1/27 |
| DeepSeek V4 Flash | .3255 | .2679 | .2696 | .1769 [.1171,.1941] | 4/27 |
| GPT-5.6 Sol | .5558 | .4879 | .4981 | .2500 [.1333,1.000] | 8/27 |
| Llama 3.3 70B | .5312 | .4528 | .4719 | .2000 [.1461,1.000] | 9/27 |
| Qwen 3.8 27B | .4324 | .4147 | .4087 | .1778 [.1524,.9441] | 6/27 |
| Run | First-pass valid | Final valid | Attempts |
|---|---|---|---|
| 1 | 43/45 (95.56%) | 45/45 | 47 |
| 2 | 41/45 (91.11%) | 45/45 | 50 |
| 3 | 40/45 (88.89%) | 45/45 | 68 |
| All | 124/135 (91.85%) | 135/135 | 165 |
| Lane 1: mechanical | Lane 2: structural | Lane 3: automated | |||||||
|---|---|---|---|---|---|---|---|---|---|
| LLM | Validate | Probe | Pass | Cov. | Prec. | F1 | Checklist | Bias | |
| Claude Opus 5 | 27 | 27 | 27 | 27 | .7173 | .4456 | .4910 | 27 | 27 |
| GPT-5.6 Sol | 27 | 27 | 27 | 27 | .2088 | .7657 | .3207 | 25 | 27 |
| Llama 3.3 70B | 22 | 20 | 17 | 20 | .3031 | .8248 | .4288 | 20 | 20 |
| Qwen 3.8 27B | 18 | 17 | 17 | 17 | .3450 | .8623 | .4796 | 17 | 17 |
| DeepSeek V4 Flash | 16 | 16 | 16 | 16 | .3753 | .8166 | .4760 | 16 | 16 |
Appendix figures & tables23 assets
Supplementary material from the paper’s appendix.
Appendix
| Track | Metric | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Game | Lane 1 Pass | 15 | 15 | 15 | 15 | 15 | 15 | 15 | 15 | 14 | – | – | – | – | – |
| Mean F1 | .345 | .095 | .321 | .634 | .468 | .183 | .610 | .492 | .127 | – | – | – | – | – | |
| Situational | First-pass | 13 | 13 | 11 | 10 | 13 | 11 | 12 | 13 | 11 | 12 | 11 | – | – | – |
| Pairwise F1 | .478 | .465 | .278 | .384 | .378 | .598 | .440 | .668 | .413 | .350 | .149 | – | – | – | |
| Cov. proxy | .500 | .550 | .400 | .700 | .400 | .533 | .450 | .300 | .600 | .667 | .767 | – | – | – | |
| Cultural | Lane 1 Pass | 10 | 10 | 10 | 10 | 9 | 10 | 8 | 10 | 9 | 9 | 8 | 8 | 10 | 10 |
| LLM | Mean SD | Median range | Equivalent SD |
|---|---|---|---|
| Claude | .0715 | .0005 | 4/9 |
| DeepSeek | .1775 | .1053 | 1/9 |
| GPT | .0618 | .0000 | 5/9 |
| Llama | .1684 | .1184 | 4/9 |
| Qwen | .3601 | .7865 | 1/9 |
| Case | Lane 1 | L2a cov | L2a prec | L2a comb | Lane 3 | Bias-free | Overall |
|---|---|---|---|---|---|---|---|
| T1.1 | Pass | 1.00 | 1.00 | 1.00 | Pass | Pass | Pass |
| T1.2 | Pass | 1.00 | 1.00 | 1.00 | Pass | Pass | Pass |
| T2.1 | Pass | 0.69 | 0.90 | 0.78 | Pass | Pass | Pass |
| T2.2 | Pass | 0.53 | 0.94 | 0.68 | Pass | Pass | Pass |
| T3.1 | Pass | 1.00 | 1.00 | 1.00 | Pass | Pass | Pass |
| T3.2 | Pass | 0.65 | 0.88 | 0.75 | Pass | Pass | Pass |
| LLM | Cand. | Lane 1 | L2a cov | L2a comb | Lane 3 | Bias-free | Overall |
|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 27 | 27/27 | 0.94 | 0.79 | 27/27 | 27/27 | 27/27 |
| Claude Opus 5 | 27 | 27/27 | 0.91 | 0.52 | 27/27 | 27/27 | 27/27 |
| Llama 3.3 70B | 27 | 27/27 | 0.89 | 0.75 | 27/27 | 27/27 | 27/27 |
| Qwen 3.8 27B | 27 | 27/27 | 0.86 | 0.82 | 27/27 | 27/27 | 27/27 |
| DeepSeek V4 Flash | 27 | 26/27 | 0.78 | 0.71 | 27/27 | 27/27 | 26/27 |
| LLM | G1 | G2 | G3 | G4 | G5 | G6 | G7 | G8 | G9 |
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | .94 / .82 | .95 / .21 | .80 / .82 | 1.0 / 1.0 | .95 / .97 | .90 / .28 | 1.0 / 1.0 | 1.0 / 1.0 | .95 / .97 |
| Claude Opus 5 | 1.0 / .79 | .74 / .10 | .92 / .69 | .90 / .46 | 1.0 / .87 | .96 / .11 | .88 / .62 | .77 / .35 | 1.0 / .68 |
| Llama 3.3 70B | .94 / .89 | .81 / .36 | .88 / .79 | 1.0 / 1.0 | .90 / .71 | .82 / .72 | 1.0 / 1.0 | .65 / .59 | 1.0 / .68 |
| Qwen 3.8 27B | .88 / .93 | .91 / .18 | .87 / .88 | .93 / .96 | .90 / .95 | .64 / .74 | .77 / .86 | .88 / .93 | .93 / .96 |
| DeepSeek V4 Flash | .82 / .82 | .63 / .15 | .71 / .61 | .97 / .98 | .90 / .95 | .63 / .39 | .65 / .79 | .77 / .86 | .93 / .81 † |
| Values formatted as Coverage / Combined . † DeepSeek recorded a single Lane-1 failure on G9 (2/3). | |||||||||
| LLM | Validate | Probe | Lane 1 |
|---|---|---|---|
| Claude Opus 5 | 27/27 | 27/27 | 27/27 (100%) |
| GPT-5.6 Sol | 27/27 | 27/27 | 27/27 (100%) |
| Llama 3.3 70B | 22/27 | 20/27 | 17/27 (62.96%) |
| Qwen 3.8 27B | 18/27 | 17/27 | 17/27 (62.96%) |
| DeepSeek V4 Flash | 16/27 | 16/27 | 16/27 (59.26%) |
| All | 110/135 | 107/135 | 104/135 (77.04%) |
| Run | Strict | L1 | L3 | Bias-free | Overall | L2a cov | L2a prec | L2a comb | Sem cov | Sem avd | Sem | States | SelfF1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol (anon.) | 13/14 | 14/14 | 14/14 | 2/14 | 14/14 | .846 | .543 | .639 | .896 | 1.000 | .945 | 8.9 | .837 |
| GPT-5.6 Sol (loc.) | 13/14 | 14/14 | 14/14 | 1/14 | 14/14 | .859 | .462 | .578 | .884 | 1.000 | .939 | 10.9 | .837 |
| Llama 3.3 (anon.) | 0/14 | 8/14 | 12/14 | 0/14 | 8/14 | .786 | .570 | .645 | .706 | 1.000 | .838 | 6.7 | .851 |
| Llama 3.3 (loc.) | 0/14 | 11/14 | 14/14 | 1/14 | 11/14 | .788 | .574 | .655 | .694 | 1.000 | .831 | 6.4 | .851 |
| Opus 5 (anon.) | 13/14 | 14/14 | 14/14 | 0/14 | 14/14 | .769 | .296 | .419 | .845 | .982 | .909 | 7.4 | .834 |
| Opus 5 (loc.) | 13/14 | 14/14 | 14/14 | 0/14 | 14/14 | .832 | .264 | .398 | .827 | 1.000 | .907 | 8.7 | .834 |
| LLM | Sem (w/o) | Sem (w/) | Sem | F1 (w/o) | F1 (w/) | F1 | SelfF1 |
|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | .945 | .939 | .006 | .639 | .578 | .061 | .837 |
| Llama 3.3 | .838 | .831 | .007 | .645 | .655 | .010 | .851 |
| Claude Opus 5 | .909 | .907 | .001 | .419 | .398 | .021 | .834 |
| Qwen 3.8 | .940 | .920 | .019 | .686 | .543 | .144 | .762 |
| DeepSeek | .879 | .869 | .011 | .678 | .667 | .011 | .821 |
| Case | GPT-5.6 | Llama 3.3 | Opus 5 | Qwen 3.8 | DeepSeek |
|---|---|---|---|---|---|
| C1 | .044 | .000 | .000 | .000 | .011 |
| C2 | .000 | .000 | .127 | .000 | .032 |
| C3 | .000 | .049 | .000 | .091 | .010 |
| C4 | .044 | .102 | .091 | .000 | .060 |
| C5 | .000 | – | .000 | .000 | .000 |
| C6 | .000 | .053 | .000 | .047 | .001 |
| Case | GPT-5.6 | Llama 3.3 | Opus 5 | Qwen 3.8 | DeepSeek | Panel |
|---|---|---|---|---|---|---|
| C1 | .913 | .817 | .957 | .913 | .913 | .903 |
| C2 | .949 | .894 | .949 | .949 | .894 | .927 |
| C3 | .817 | .866 | .866 | .866 | .854 | .854 |
| C4 | .913 | .764 | .866 | .913 | .764 | .844 |
| C5 | 1.000 | .817 | 1.000 | .957 | .913 | .937 |
| C6 | .957 | .764 | .817 | .913 | .957 | .882 |
| Case | Model | Original | India | China | Native Am. | No loc. |
|---|---|---|---|---|---|---|
| C9 | GPT-5.6 | 8 / LOW | 10 / EXT | 9 / HIGH | 7 / LOW | 12 / EXT |
| C9 | Llama 3.3 | 14 / HIGH | 11 / EXT | 10 / HIGH | 9 / EXT | 8 / EXT |
| C9 | Claude Opus 5 | 9 / LOW | 12 / HIGH | 8 / LOW | 11 / HIGH | 7 / LOW |
| C9 | Qwen 3.8 | 11 / LOW | 13 / LOW | 10 / LOW | 8 / HIGH | 14 / EXT |
| C9 | DeepSeek | 9 / HIGH | 6 / EXT | 11 / HIGH | – / – | – / – |
| C13 | GPT-5.6 | 8 / LOW | 9 / LOW | 7 / LOW | 8 / LOW | 12 / EXT |
LLM World Models
Large language model world models predict how environments change so agents can plan, learn, and evaluate actions before execution.
See all 38 papers