Link the released ALFWorld model repos

README.md

@@ -12,19 +12,20 @@ tags:
 
 # EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
 
-> **Coming soon.** Trained models will be released here. Follow [github.com/Gnonymous/EVOKE](https://github.com/Gnonymous/EVOKE) for updates.
+> **ALFWorld models are released.** See the repositories below; evaluation code is at [github.com/Gnonymous/EVOKE](https://github.com/Gnonymous/EVOKE).
 
 **[🌐 Project Page](https://gnonymous.github.io/EVOKE)** · **[💻 Code](https://github.com/Gnonymous/EVOKE)** · **[📑 Paper (arXiv:2609.38334)](https://arxiv.org/abs/2609.38334)**
 
 **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.
 
-## Planned release
+## Models
 
-| Backbone | Benchmarks |
-| --- | --- |
-| Qwen2.5-3B-Instruct | ALFWorld, WebShop, search-based QA |
-| Qwen2.5-7B-Instruct | ALFWorld, WebShop, search-based QA |
-| Qwen3-1.7B | ALFWorld, WebShop, search-based QA |
+| Model | Base model | Benchmark |
+| --- | --- | --- |
+| [Gnonymous/EVOKE-ALFWorld-7B](https://huggingface.co/Gnonymous/EVOKE-ALFWorld-7B) | Qwen2.5-7B-Instruct | ALFWorld |
+| [Gnonymous/EVOKE-ALFWorld-3B](https://huggingface.co/Gnonymous/EVOKE-ALFWorld-3B) | Qwen2.5-3B-Instruct | ALFWorld |
+
+Both repositories contain full models, each with its own license. Evaluation code: [github.com/Gnonymous/EVOKE](https://github.com/Gnonymous/EVOKE).
 
 ## Citation