Consider adding FlashAdventure (EMNLP 2025 Main) to the list

[ahnjaewoo]

Thanks for setting up this repository! I would like to add our paper, FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games, to this list.
It best fits the Video Adventure Games & Benchmark sections.

🎓 Venue: EMNLP 2025 Main Conference

🔗 Website: https://ahnjaewoo.github.io/flashadventure/
📄 Paper: https://arxiv.org/abs/2509.01052
🌎 Code: https://github.com/ahnjaewoo/FlashAdventure

TL;DR: Key Findings

• Current GUI agents struggle with full story arc completion (best: 5.88% success rate).
• COAST improves goal / milestone completion by 5.88 / 2.78 percentage points over the baseline.
• Still, significant gap remains between GUI agents and human performance (97.06% vs 5.88%).
• Agents exhibit weak planning, poor visual perception, and deficient lateral thinking.

Thanks!

[Bayi-Hu]

Got it! Thanks for recommendation.