# Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization

arXiv: https://arxiv.org/abs/2603.17692 · HTML: https://mlsanity.com/paper/2603.17692/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [FinBERT: Financial Sentiment Analysis with Pre-trained Language Models](https://mlsanity.com/paper/1908.10063/) (2019)
- [Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models](https://mlsanity.com/paper/2304.07619/) (2023)
- [A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem](https://mlsanity.com/paper/1706.10059/) (2017)
- [Temporal Relational Ranking for Stock Prediction](https://mlsanity.com/paper/1809.09441/) (2018)
- [Deep Reinforcement Learning for Trading](https://mlsanity.com/paper/1911.10107/) (2019)
- [Your AI, Not Your View: The Bias of LLMs in Investment Analysis](https://mlsanity.com/paper/2507.20957/) (2025)
- [LiveTradeBench: Seeking Real-World Alpha with Large Language Models](https://mlsanity.com/paper/2511.03628/) (2025)

## Built on by (most cited first, 4 of 4)

- [Agentic Trading: When LLM Agents Meet Financial Markets](https://mlsanity.com/paper/2605.19337/) (2026)
- [EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents](https://mlsanity.com/paper/2609.17632/) (2026)
- [MemGuard-Alpha: Limits of Membership Inference for Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting](https://mlsanity.com/paper/2603.26797/) (2026)
- [DeXposure-Claw: An Agentic System for DeFi Risk Supervision](https://mlsanity.com/paper/2606.19501/) (2026)

## Abstract (arXiv)

For LLM trading agents to be genuinely trustworthy, they must demonstrate understanding of market dynamics rather than exploitation of memorized ticker associations. Building responsible multi-agent systems demands rigorous signal validation: proving that predictions reflect legitimate patterns, not pre-trained recall. We address two sources of spurious performance: memorization bias from ticker-specific pre-training, and survivorship bias from flawed backtesting. Our approach is to blindfold the agents--anonymizing all identifiers--and verify whether meaningful signals persist. BlindTrade anonymizes tickers and company names, and four LLM agents output scores along with reasoning. We construct a GNN graph from reasoning embeddings and trade using PPO-DSR policy. On 2025 YTD (through 2025-08-01), we achieved Sharpe 1.40 +/- 0.22 across 20 seeds and validated signal legitimacy through negative control experiments. To assess robustness beyond a single OOS window, we additionally evaluate an extended period (2024--2025), revealing market-regime dependency: the policy excels in volatile conditions but shows reduced alpha in trending bull markets.