Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 25 days ago • 246
PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers Paper • 2605.26730 • Published 26 days ago • 16
Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs Paper • 2505.11277 • Published May 16, 2025 • 29
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 26 days ago • 429