Tag
Central bankers are discussing a future where AI better understands monetary policy than humans, potentially requiring the Federal Reserve to adjust communication to avoid exploitation by trading agents.
The article explains the architectural difference between deterministic trading bots and AI-driven trading agents, detailing agent components, tradeoffs, and an autonomy-level framework.
The author recounts an incident where their autonomous trading agents locked themselves out of their broker account, and shares lessons learned about running AI agents in production.
Raven-Agent is the first autonomous trading agent for prediction markets, featuring an explicit belief-to-trade layer. It achieves positive returns on a controlled replay, bridging the gap between calibrated forecasts and profitable trading.
This paper investigates the behavioral alignment and representation dynamics of LLM agents in financial trading, introducing the TradeArena testbed and finding measurable pre-failure signatures in planning embeddings that can predict drawdowns with high accuracy across multiple frontier models and stress conditions.