Morgan Stanley's ALPHALAB: Multi-Agent Research Across Optimization Domains — Brendan Rappazzo
Morgan Stanley's 30-person PhD team built a multi-agent system to automate quantitative research across trading desks.
“it really felt possible for the first time with like with Opus 4.5 and with, you know, these harnesses like Claude Code and Codex, where it really felt like the models were at a point where they could do these long-horizon tasks”
Morgan Stanley's ALPHALAB team is deploying multi-agent AI to automate quantitative research, including hyperparameter tuning, model ensembling, and cross-desk algorithm transfer (e.g., credit bonds to muni bonds). The team credits a December 2025 inflection point—specifically Claude Opus 4.5 and coding agents like Claude Code and Codex—as the moment long-horizon agentic research became viable. This is a meaningful signal that frontier financial institutions are moving from AI experimentation to production agentic workflows for core research functions.