Microsoft and SJTU open-source Argus, an agent that ran 1,548 hours and solved a 20-year-old math problem
jiqizhixin · x · 2026-09-16
Microsoft and Shanghai Jiao Tong University have open-sourced Argus, a general agent inference runtime for long-horizon research tasks. In testing, the agent ran continuously for 1,548 hours across 27 research campaigns, requested human intervention only once every 40.7 hours on average, maintained a 95.1%–98.7% duty cycle, and solved a 20-year-old open math problem along the way.
Most agent systems stall when humans leave: decisions require human grants, and without dense reward feedback agents become sluggish. Argus is built on four principles:
- Evidence-driven: every claim must be backed by verifiable evidence;
- Self-evolution: agents learn from their own research history;
- Multi-agent collaboration: separate roles with independent contexts but shared workspaces to avoid local hill-climbing;
- Core-vertical decoupling: the core handles permissions, evidence submission, and human boundaries, while verticals define specific research tasks.
More from coding & agent
- Microsoft's MemSteer turns unlabeled user histories into agent memory supervision — MicrosoftResearch · 2026-11-02
- She fired herself from her own Instagram: AI agent runs the account, views up 82.3% — heyshrutimishra · 2026-11-02
- Sourcegraph: AI writes code faster than teams can review it, driving more outages — AI Engineer · 2026-11-02
- Tsinghua & Microsoft's HarnessMM cuts agent token use by up to 87.93% while raising success rate — rohanpaul_ai · 2026-11-02
- GitHub launches Agent HQ: Anthropic, OpenAI, Google coding agents in Copilot — emmanuelvivier · 2026-11-02
- DeepSeek open-sources Super-Agent, a coding agent that reads team chats to minimize human input — emmanuelvivier · 2026-11-02