3 papers
cs.AI2026
PLE: Physical-Engineering's Last Exam
Rujun Han, Yufan Zhuang, Arijit Ray +10
Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing be…
cs.AI2026
VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
Caiqi Zhang, Rujun Han, Zifeng Wang +4
As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be strengthened…
cs.AI2026
EnvHarness: Awakening Static Worlds for Agent Learning
Chengsong Huang, Zifeng Wang, Rujun Han +14
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While r…