Steering Geometry: Validating Human Value Geometry in LLM Steering Space Paper • 2609.06289 • Published 20 days ago • 31
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 17 days ago • 174
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration Paper • 2607.15257 • Published Jul 16 • 70
Metacognition in LLMs: Foundations, Progress, and Opportunities Paper • 2607.11881 • Published Jul 13 • 27