Projects / Research
slay-the-spire-bench
Benchmark of language-model planning on Slay the Spire tasks: turn sequencing, combat, card recognition and Act 1 rollouts, including a comparison of JSON and plain-English prompts.
Projects / Research
Benchmark of language-model planning on Slay the Spire tasks: turn sequencing, combat, card recognition and Act 1 rollouts, including a comparison of JSON and plain-English prompts.