From c4152d694616c55a1e3be28bafe2e848c6424b79 Mon Sep 17 00:00:00 2001 From: Yijia-Xiao Date: Wed, 16 Sep 2026 21:45:08 +0000 Subject: [PATCH] docs: note the backtest command and remembered selections --- README.md | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 6f4a0c3d6..c70e68bf6 100644 --- a/README.md +++ b/README.md @@ -176,7 +176,7 @@ Launch the interactive CLI: tradingagents # installed command python -m cli.main # alternative: run directly from source ``` -You will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more. +You will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more. Your previous run's answers come back as the defaults, so pressing Enter accepts them. The `TRADINGAGENTS_*` variables in `.env` still skip their step entirely. ### Markets and tickers @@ -302,6 +302,12 @@ result = run_backtest(["NVDA", "AAPL"], dates, config, selected_analysts=["marke print(summarize(TradingMemoryLog({"memory_log_path": str(result.log_path)})).render()) ``` +From the CLI: + +```bash +tradingagents backtest NVDA,AAPL --start 2026-06-01 --end 2026-08-01 --every 7 +``` + Each cell is scored on realized alpha against the instrument's regional benchmark, grouped by rating. Your own decision log is never written to, and re-running the same grid with `run_id=result.run_id` skips the cells that already ran, so an interrupted sweep continues where it stopped. ## Reproducibility