Multi-Agent Research: How 6 LLM Teams Analyze 900 Stocks

Originally published at https://nousergon.ai/blog/posts/multi-agent-research/ In Post 1 , I introduced Nous Ergon — an autonomous trading system that splits intelligence across four layers: LLM agents for research judgment, ML for pattern recognition, deterministic rules for execution, and a backtester for system-wide learning. This post goes inside the Research module — the layer where LLMs are found hard at work. What a Weekend Run Looks Like Over the weekend, an AWS Lambda fires. It loads the S&P 500 and S&P 400 — roughly 900 mid-to-large-cap US stocks — along with recent price history, and then distributes them across six sector-specialized teams that run in parallel. Each team screens, analyzes, and debates their sector's best opportunities. A CIO agent evaluates the top picks across all teams and decides which stocks enter or exit the portfolio. The pipeline writes a single signals.json file to S3 that the rest of the system — Predictor, Executor, Backtester — consumes. By the ti