Review
Aug 2026
Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks
Results show that a fixed-weight, self-evolving harness can revise, recover, and accumulate verified approaches while producing structured trajectories for future supervised and reinforcement learning.
Boxiu Li, Zimo Wen, Yijia Fan et al.
· 2 citations
· ⚡1