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

ALFWorld models are released. See the repositories below; evaluation code is at github.com/Gnonymous/EVOKE.

🌐 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.

Models

Model	Base model	Benchmark
Gnonymous/EVOKE-ALFWorld-7B	Qwen2.5-7B-Instruct	ALFWorld
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.

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}
}