2 papers
cs.LG2026
Search Self-play: Pushing the Frontier of Agent Capability without Supervision
Hongliang Lu, Yuhang Wen, Pengyu Cheng +7
Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on well-crafted task queries and cor…
cs.CV2025
ParkFormer: A Transformer-Based Parking Policy with Goal Embedding and Pedestrian-Aware Control
Jun Fu, Bin Tian, Haonan Chen +2
Autonomous parking plays a vital role in intelligent vehicle systems, particularly in constrained urban environments where high-precision control is required. While traditional rul…