ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL Paper • 2608.28476 • Published Aug 28 • 31
BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language Paper • 2606.22138 • Published Jun 20 • 26
R-Select Collection High-quality Multi-metric selected datasets for efficient LLM post-training • 3 items • Updated Jun 17
ACC: Compiling Agent Trajectories for Long-Context Training Paper • 2605.21850 • Published May 21 • 61
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control Paper • 2605.15963 • Published May 15 • 16
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs Paper • 2604.10480 • Published Apr 12 • 20
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale Paper • 2604.04771 • Published Apr 6 • 103