Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending entities, post-cutoff events, and more. This world-knowledge bottleneck is structural: generators are trained on fixed corpora, but the visual world is open-ended. We construct SearchGen-20K and SearchGen-Bench, with 20,839 prompts spanning twelve failure categories and twenty-two domains, paired with a pre-executed multimodal SearchGen-Corpus-1M to support offline, reproducible research. On SearchGen-Bench, frontier
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorHaozhe Wang →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorWeijia Feng →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorJinpeng Yu →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorChe Liu →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorPing Nie →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorFangzhen Lin →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorJiaming Liu →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorRuihua Huang →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorJimmy Lin →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorWenhu Chen →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
- Linked via arxiv authorCong Wei →
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation