ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs Paper • 2610.15368 • Published 8 days ago • 5
LEGO-Anything: Coding Agents for 3D Scene Reconstruction Paper • 2609.36380 • Published 21 days ago • 131
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published Sep 14 • 333
MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning Paper • 2605.14212 • Published May 14 • 19
Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following Paper • 2511.21662 • Published Nov 26, 2025 • 12
UniGame: Turning a Unified Multimodal Model Into Its Own Adversary Paper • 2511.19413 • Published Nov 24, 2025 • 21