EvolveTrade Paper: Evolving Agent System Prompts Beats Fixed-Prompt Trading Baselines
dair_ai · x · 2026-09-23
A recommended paper for agent harness tuning, EvolveTrade treats a trading agent's system prompt as its policy: after each trading interval, a separate Policy Agent reads decision traces and realized returns and rewrites the prompt while the backbone model stays frozen. Across several market regimes and two backbones, the evolved agent beats fixed-prompt baselines on Sharpe ratio and cumulative return in most settings, with rewritten prompts pushing the agent toward more code-based analysis and regime-fitting signals.
More from coding & agent
- LiteParse v2.14.6 Hits 2.8ms/Page, 1.5x Faster Than Nearest Local Parser — llama_index · 2026-09-23
- AngelX Agent Dominates Omp and Opencode in Head-to-Head Autoresearch Bench — tokenbender · 2026-09-23
- Vercel Ship SF lineup: Rauch to interview Shopify CEO Tobi on agentic commerce, Oct 15 — evilrabbit_ · 2026-09-23
- One Prompt, 40 Sub-agents: Fable 5.1 Builds a Computer-Use Agent in a Day — every · 2026-09-23
- Hamel Husain: refresh stale eval datasets with regular error analysis, retire passing ones — HamelHusain · 2026-09-23
- RealSense launches people-detection challenge, best project wins a D421 camera — chrismatthieu · 2026-09-23