« WEB-SHEPHERD » : différence entre les versions
Aucun résumé des modifications |
Aucun résumé des modifications |
||
| Ligne 17 : | Ligne 17 : | ||
== Source == | == Source == | ||
[https://huggingface.co/papers/2505.15277 | [https://huggingface.co/papers/2505.15277 Source : huggingface] | ||
[[Catégorie:vocabulary]] | [[Catégorie:vocabulary]] | ||
Version du 23 mai 2025 à 11:25
en construction
Définition
XXXXXXXXX
Français
XXXXXXXXX
Anglais
WEB-SHEPHERD
The first process reward model (PRM) specifically designed for web navigation tasks. It addresses the challenges of evaluating web agent trajectories at a step-by-step level, which is crucial for improving agent performance in long-horizon web tasks. WEB-SHEPHERD is designed as a process reward model that evaluates web navigation trajectories at each step. The method works in two main stages: checklist generation and reward modeling with the checklist.
Source
