FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Paper • 2606.12087 • Published 3 days ago • 71
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 3 days ago • 104
From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning Paper • 2606.07190 • Published 8 days ago • 34
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published 10 days ago • 115
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published 12 days ago • 228
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI Paper • 2605.26112 • Published 19 days ago • 9