3 papers
cs.AI2026
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Jiaming Wang, Ziteng Feng, Jiangtao Wu +8
Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent…
cs.HC2026
SPRITE: From Static Mockups to Engine-Ready Game UI
Yunshu Bai, RuiHao Li, Hao Zhang +3
Game UI implementation requires translating stylized mockups into interactive engine entities. However, current "Screenshot-to-Code" tools often struggle with the irregular geometr…
cs.AI2025
Zero-shot 3D Map Generation with LLM Agents: A Dual-Agent Architecture for Procedural Content Generation
Lim Chien Her, Ming Yan, Yunshu Bai +2
Procedural Content Generation (PCG) offers scalable methods for algorithmically creating complex, customizable worlds. However, controlling these pipelines requires the precise con…