EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making

Coming soon. Trained models will be released here. Follow github.com/Gnonymous/EVOKE for updates.

🌐 Project Page · 💻 Code · 📑 Paper (arXiv: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

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

Citation

@article{guo2026evoke,
  title={EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making},
  author={Guo, Yuhan and Liu, Jinming and Xu, Liang and Li, Ziqiang and Huang, Jianguo and Wang, Zhicheng and Zhu, Hu and Chen, Qiuyu and Wei, Yuntao and Jin, Xin and Zeng, Wenjun},
  journal={arXiv preprint arXiv:2609.38334},
  year={2026}
}