ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Paper • 2603.10160 • Published • 26
Interesting Papers
-
-
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
Paper • 2603.12262 • Published • 31 -
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
Paper • 2603.13594 • Published • 149 -
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 140 -
LightThinker++: From Reasoning Compression to Memory Management
Paper • 2604.03679 • Published • 38 -
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
Paper • 2604.22446 • Published • 121