From 62c76c77f52045b7c2282edee1f921d23e090e3a Mon Sep 17 00:00:00 2001 From: Avaya Aggarwal Date: Mon, 25 May 2026 23:25:00 +0530 Subject: [PATCH] docs: mention agent swarm branch --- README.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/README.md b/README.md index 7b5093f0..c0b1f8e8 100644 --- a/README.md +++ b/README.md @@ -52,6 +52,25 @@ analyze ──► hypothesize ──► backtest ──► reflect --- +### Experimental Agent Swarm Branch + +The `agent-swarm-method` branch explores a multi-agent version of AgentQuant. It decomposes the research loop into specialized agents: + +- **Memory Agent** retrieves and stores strategy patterns across runs. +- **Regime Analyst** builds the market/macro context used by downstream agents. +- **Strategy Specialists** generate proposals for momentum, mean reversion, volatility, and trend-following approaches. +- **Critic Agent** pre-screens proposals before expensive backtests. +- **Backtest Coordinator** validates approved proposals across multiple time windows and ranks by robustness. + +That branch is intentionally experimental and sits alongside the main ReAct pipeline. To inspect it: + +```bash +git checkout agent-swarm-method +pytest tests/test_swarm.py -v +``` + +--- + ## Quick Start **Prerequisites:** Python 3.10+, Google Gemini API Key (optional — works without it via grid search).