Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
2
7
4
6
GUI agents learn faster and generalize better with a new reward shaping technique that dynamically adapts to successful exploration trajectories, outperforming fixed reward schemes.
Current LLM evaluation benchmarks often conflate chatbots and true AI agents, leading to misaligned research efforts, but this survey provides a framework for targeted evaluation based on environmental complexity and agent capabilities.
