Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,7 @@ PDDL2PRM is the dataset introduced in:
|
|
| 12 |
Raffaele Pisano and Roberto Navigli, ACL 2026
|
| 13 |
|
| 14 |
Project page & paper: https://babelscape.github.io/prm-meets-planning/
|
|
|
|
| 15 |
arXiv: https://arxiv.org/abs/2604.17957
|
| 16 |
|
| 17 |
The paper proposes using symbolic planning problems written in **Planning Domain Definition Language (PDDL)** to generate precise step-level rewards for reasoning trajectories. In PDDL, actions, states, preconditions, effects, and goals are explicitly defined, so intermediate reasoning steps can be evaluated automatically.
|
|
|
|
| 12 |
Raffaele Pisano and Roberto Navigli, ACL 2026
|
| 13 |
|
| 14 |
Project page & paper: https://babelscape.github.io/prm-meets-planning/
|
| 15 |
+
|
| 16 |
arXiv: https://arxiv.org/abs/2604.17957
|
| 17 |
|
| 18 |
The paper proposes using symbolic planning problems written in **Planning Domain Definition Language (PDDL)** to generate precise step-level rewards for reasoning trajectories. In PDDL, actions, states, preconditions, effects, and goals are explicitly defined, so intermediate reasoning steps can be evaluated automatically.
|