Argus Enables Autonomous Research for Long-Term Agents

Microsoft and Shanghai Jiao Tong University have open-sourced Argus, a general agent reasoning runtime designed for long-term research tasks. This system enables agents to extend across multiple domains and conduct continuous research over several days without dense standard feedback.

The researchers used design principles such as evidence-driven reasoning, self-evolution, multi-agent collaboration, and decoupling of core and domain-specific components to achieve this goal.

The Argus system has been tested on 27 campaigns and 1,548 hours of wall-clock time, with an average of one human intervention requested every 40.7 hours. The workload utilization ranges from 95.1% to 98.7%.