Personal-Agent Mediated Recommendation with Cross-Platform User History Paper • 2610.07588 • Published 3 days ago • 5
Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards Paper • 2510.01167 • Published Oct 1, 2025 • 3
From Selection to Generation: A Survey of LLM-based Active Learning Paper • 2502.11767 • Published Feb 17, 2025 • 3