Memory as Plans: World-Action Modeling with Memory-Grounded Planning Paper • 2609.11561 • Published 4 days ago • 36
RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests Paper • 2608.27831 • Published 14 days ago • 32
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training Paper • 2608.26730 • Published 18 days ago • 155
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes Paper • 2609.03796 • Published 11 days ago • 235
SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation Paper • 2608.18565 • Published 26 days ago • 116
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers Paper • 2608.06867 • Published Aug 7 • 111
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models Paper • 2608.08627 • Published Aug 9 • 14
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents Paper • 2608.03509 • Published Aug 4 • 24