Microsoft and SJTU open-source Argus: research agent ran 1,548 hours, solved 20-year math problem
xiaohu · x · 2026-09-16
Microsoft and Shanghai Jiao Tong University released and open-sourced Argus, a general agent inference runtime for long-horizon research tasks. Key numbers: one run lasted 1,548 hours across 27 research campaigns, requesting human intervention only once every 40.7 hours on average, with a duty cycle of 95.1%–98.7% — and it solved a 20-year-old open math problem along the way.
The authors argue most agent systems stall once humans step away: 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: a core layer handles permissions, evidence submission, and human boundaries, while verticals define the actual research tasks
More from coding & agent
- Workshop 0.3.1: Open-Source Execution Architecture for Grounded AI Work — Promptmethus · 2026-09-16
- Energon: Open-source self-hosted storage and publishing service built for AI agents — kieranklaassen · 2026-09-16
- lateinteraction: let agents compile expensive LLM calls into cheap AI functions, likely via DSPy — lateinteraction · 2026-09-16
- Dev builds MCP server feeding Claude curated UI/UX patterns, seeks feedback — Separate-Topic4883 · 2026-09-16
- SwiftUI co-creator defends client-side animations: dropping Core Animation was deliberate — JordanMorgan10 · 2026-09-16
- Building a browser game inside a Gaussian splat made in World Labs Marble — theworldlabs · 2026-09-16