LLM Agents Improve Trading Risk-Adjusted Returns
Takanobu Kawahara (arXiv preprint submitted Feb 26, 2026) proposes a multi-agent LLM trading framework that decomposes investment analysis into fine-grained tasks rather than coarse instructions. The system is evaluated on Japanese stock prices, financial statements, news, and macro data using leakage-controlled backtesting, where fine-grained decomposition improves risk-adjusted returns and alignment of intermediate outputs drives performance. Portfolio optimization leveraging low index correlation and output variance further boosts returns.
Key Points
- 1Demonstrates fine-grained task decomposition yields higher risk-adjusted returns in leakage-controlled backtests on Japanese stocks
- 2Identifies alignment between intermediate analytical outputs and decision preferences as a primary driver of system performance
- 3Recommends portfolio optimization leveraging low index correlation and output variance to enhance real-world trading returns
Scoring Rationale
Strong practical results and actionable methods, limited by single preprint evaluation on Japanese stocks.
Sources
Public references used for this report.
Practice with real FinTech & Trading data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all FinTech & Trading problems
