Link project page and code
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ tags:
|
|
| 14 |
|
| 15 |
> **Coming soon.** Trained models will be released here. Follow [github.com/Gnonymous/EVOKE](https://github.com/Gnonymous/EVOKE) for updates.
|
| 16 |
|
|
|
|
|
|
|
| 17 |
**EVOKE** is a post-training method that elicits the world knowledge already inside pretrained LLM agents, so that they decide by the consequences of their actions rather than by contextual habits. It holds the state fixed, swaps in alternative goals, and trains the policy to rank the same candidate actions under each goal, with no world-model module and no inference-time planning.
|
| 18 |
|
| 19 |
## Planned release
|
|
|
|
| 14 |
|
| 15 |
> **Coming soon.** Trained models will be released here. Follow [github.com/Gnonymous/EVOKE](https://github.com/Gnonymous/EVOKE) for updates.
|
| 16 |
|
| 17 |
+
**[🌐 Project Page](https://gnonymous.github.io/EVOKE)** · **[💻 Code](https://github.com/Gnonymous/EVOKE)** · **📑 Paper (coming soon)**
|
| 18 |
+
|
| 19 |
**EVOKE** is a post-training method that elicits the world knowledge already inside pretrained LLM agents, so that they decide by the consequences of their actions rather than by contextual habits. It holds the state fixed, swaps in alternative goals, and trains the policy to rank the same candidate actions under each goal, with no world-model module and no inference-time planning.
|
| 20 |
|
| 21 |
## Planned release
|