Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics

TL;DR

The paper introduces Semantic State Abstraction Interfaces (SSAI), a framework for mapping unstructured text into interpretable coordinates to improve decision systems, evaluated on financial data with mixed results.

Contribution

It presents SSAI as a reusable, interpretable diagnostic framework for sparse-text decision systems, with evaluation protocol and instantiation on financial news data.

Findings

A four-axis SSAI achieved 307.2% return and Sharpe 1.067 in portfolio tests.

Gains over buy-and-hold were not statistically robust and depended on specific baselines.

Ridge and RL diagnostics helped distinguish representation effects from optimizer effects.

Abstract

We introduce Semantic State Abstraction Interfaces (SSAI): a methodological template for mapping sparse unstructured text into $K$ auditable, named coordinates with neutral defaults on no-news days, designed to separate representation hypotheses from optimisation variance in sequential decision systems. Our contribution is the framework and its evaluation protocol, not a claim that SSAI outperforms denser alternatives. We instantiate SSAI with $K=4$ axes (sentiment, risk, confidence, volatility forecast) on a US-equity panel (30 NASDAQ-100 names, FNSPID news, 2019--2023 test), and evaluate it across direct factor portfolios, supervised ridge forecasters, and RL agents (DP-PPO, SAC) that share the same fixed $\phi$. The four-factor factor portfolio reaches 307.2% cumulative return and Sharpe 1.067, but apparent gains versus buy-and-hold (243.6%) fail coverage-stratified controls, reverse at $\geq 0.2$% costs, and are statistically fragile versus a sentiment-only baseline; a PC1 composite and a FinBERT portfolio baseline are stronger ranking signals in this setting. Ridge and RL blocks diagnose representation versus optimiser effects. We position SSAI as an interpretability-performance diagnostic and reusable protocol for sparse-text decision systems.