falsify-ledger.* TradingAgents (arXiv:2412.20138, ~94,700 GitHub stars) is probably the most...
TradingAgents paper claims LLM agents outperformed buy-and-hold (26.62% vs -5.23%); verification reveals buy-and-hold gained 9.12%, a fatal baseline error. Tech leaders: LLM research needs pre-registered verification before deploying agent frameworks for trading or infrastructure systems.
falsify-ledger.*
TradingAgents (arXiv:2412.20138, ~94,700 GitHub stars) is probably the most visible
"LLM agents trade stocks" project right now. The headline result: a multi-agent LLM
framework earned a 26.62% cumulative return on AAPL with a Sharpe ratio of 8.21 between
2024-06-19 and 2024-11-19, while buy-and-hold supposedly lost 5.23% over the same
TradingAgents just hit 82,356 GitHub stars and 15,978 forks in roughly 17 months — and yet most...
A 20-year academic study found LLM-based AI trading strategies consistently underperformed simple buy-and-hold investing across…
Vendor 'actual' earnings get silently revised after the fact. We measured how much look-ahead bias that injects into an LLM…
After months of letting the agent build technical indicator bots, we finally asked it to run the...
7 frontier LLMs. $100K each. Same prompts, same tools, same data. Different brains. Here's the architecture.
Frontier LLM agents waste 28–64% of tokens on doomed tasks, BAGEN reveals. Learn how budget interval estimation and early…
