open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-26 17:13:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add quantum lock answer format hint

Browse source
This commit is contained in:
Andreas Koepf 2025-02-02 22:35:43 +01:00
parent 63a8c94d85
commit 6ecd25c283
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
reasoning_gym/graphs/quantum_lock.py
View file

@ -28,7 +28,7 @@ class QuantumLockDataset(ProceduralDataset):
self._prompt_templates = [
"""\
In front of you are some buttons, a light, and a number. The light will toggle between red and green whenever you press a button. Each button performs a mathematical operation to the number, but the operation may depend on the state of the light.
You must press the shortest correct sequence of buttons to reach the target value.
You must press the shortest correct sequence of buttons to reach the target value. Your answer should be a sequence of buttons separated by '→', for example: A → B → C
Start: {initial_value} ({initial_state})
Target: {target_value}