The study investigates whether adding inference-time reasoning to large language models (LLMs) improves trading performance. Using a controlled experiment across DeepSeek, GPT, and Gemini models, the authors varied reasoning effort while keeping other variables constant and evaluated over a full year of U.S. equities under three input conditions. Results show that additional reasoning does not reliably increase net portfolio returns and can even lead to nonmonotonic performance and unstable outcomes.
arXiv:2608. 06108v1 Announce Type: new Abstract: Investment competence is inherently personalized: the same market evidence can justify different actions for investors with different goals, horizons, portfolios, and risk boundaries.
arXiv:2605. 03460v3 Announce Type: replace Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail in the financial domain, which exhibits unique characteristics.
arXiv:2606. 24950v1 Announce Type: new Abstract: Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text.
arXiv:2609.36914v1 Announce Type: new Abstract: Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning,...
The paper introduces the Token Economy Score (TES), a metric that quantifies the accuracy gain of reasoning-capable large language models relative to non-reasoning baselines, normalized by token generation cost. An empirical study across 151 runs on seven diverse benchmarks shows that task structure—such as sequential inference chains—predicts higher TES, while knowledge-recall tasks yield lower TES despite difficulty. The analysis also reveals diminishing returns at higher reasoning effort and highlights how deployment context, via Reasoning Cost Share and Deployment Cost Multiplier, can alter the economic viability of reasoning workloads.
The paper addresses look‑ahead bias in large language models (LLMs) used for financial prediction, which arises because LLMs are trained on long time‑series data. It proposes a low‑cost solution that adjusts the logits of a base model at inference time using two smaller, specialized models—one fine‑tuned to forget certain information and another to retain it. Experiments show that this method removes both verbatim and semantic knowledge, corrects biases, and outperforms previous approaches.
arXiv:2603. 19225v3 Announce Type: replace-cross Abstract: Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics.
arXiv:2608.22852v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific inv...
arXiv:2605.24564v2 Announce Type: replace Abstract: Backtesting large language models (LLMs) on historical financial data is unreliable when their pre-training data include the evaluated events. An L...
arXiv:2607. 10286v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value.
arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasonin...
The paper introduces a framework that uses large language models (LLMs) to generate natural‑language narratives explaining cross‑sectional stock return predictions. It combines temporal Shapley additive explanations (SHAP) from an XGBoost model with historical regime analogs to provide context. A controlled study shows that progressively externalizing numerical and relational reasoning improves evidence faithfulness and accuracy, while historical analogs boost human‑rated usefulness.