Morgan Stanley's ALPHALAB: Multi-Agent Research Across Optimization Domains — Brendan Rappazzo
Morgan Stanley has built AlphaLab, a system with multiple AI agents that work together to solve research problems.
You describe the problem in plain English, and the system writes code, runs tests, manages computational jobs, and performs statistical analyses autonomously. A strategy agent proposes experiments and worker agents execute them, all presented in a concise format that humans can review and approve before the system optimizes. Morgan Stanley open-sourced it and is already using it internally to find real improvements in areas such as models and credit forecasting.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More from AI Engineer
Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca
AI Engineer 23 Oct
Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg
AI Engineer 23 Oct
Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens
Techmeme 4 h ago
Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount
Techmeme 6 h ago