Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models

• URL: http://arxiv.org/abs/2604.16862v1
• Date: Sat, 18 Apr 2026 06:24:41 GMT
• Title: Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models
• Abstract summary: Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns.<n>We propose a structured framework for training and evaluating such models. Central to our approach is a curated, multiple-choice question (MCQ) dataset derived from classic textbooks and historical markets.
• Score: 13.434482682938842
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns and how it should be trained and evaluated in noisy markets lacking ground truth. We propose a structured framework for training and evaluating such models. Central to our approach is a curated, multiple-choice question (MCQ) dataset derived from classic textbooks and historical markets, verified by an AI committee, enriched with structured reasoning traces, and augmented to reduce shortcut learning. To evaluate whether performance on isolated MCQs generalizes to real-world trading, we introduce a two-stage protocol combining test-set evaluation with an MCQ-based chronological trading simulation. Extensive evaluations across market regimes provide statistically robust evidence that open models trained with our framework exhibit competitive, risk-aware behavior over time, outperform open-source baselines, and approach frontier-model performance at smaller scale. We release the dataset and evaluation framework to support further research.

Related papers

• Evaluation of Agents under Simulated AI Marketplace Dynamics [72.02953516461965]
  We introduce a simulation-based paradigm that evaluates information access systems as participants in a competitive marketplace.<n>We formalize the framework and outline a research agenda, motivated by business and economics, around marketplace simulation, metrics, optimization, and adoption in evaluation campaigns like TREC.
  arXiv  Detail & Related papers  (2026-04-15T15:01:36Z)
• Exploring a New Competency Modeling Process with Large Language Models [0.0]
  This study proposes a new competency modeling process built on large language models (LLMs)<n> Specifically, we leverage LLMs to extract behavioral and psychological descriptions from raw textual data.<n>We introduce a learnable parameter that adaptively integrates different information sources, enabling the model to determine the relative importance of behavioral and psychological signals.
  arXiv  Detail & Related papers  (2026-02-13T16:46:51Z)
• Confidence as a Reward: Transforming LLMs into Reward Models [54.98336080630691]
  Confidence-as-a-Reward (CRew) is a training-free method that utilizes token-level confidence in the model's final answers as a proxy for reward.<n>We show that CRew outperforms existing training-free reward approaches on the MATH500 and RewardMATH benchmarks.<n>We propose CRew-DPO, a training strategy that constructs preference data from confidence scores combined with correctness signals.
  arXiv  Detail & Related papers  (2025-10-15T12:51:47Z)
• Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading [57.28635022507172]
  TiMi is a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment.<n>We propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection.
  arXiv  Detail & Related papers  (2025-10-06T13:08:55Z)
• Your AI, Not Your View: The Bias of LLMs in Investment Analysis [62.388554963415906]
  In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data.<n>These conflicts are especially problematic in real-world investment services, where a model's inherent biases can misalign with institutional objectives.<n>We propose an experimental framework to investigate emergent behaviors in such conflict scenarios, offering a quantitative analysis of bias in investment analysis.
  arXiv  Detail & Related papers  (2025-07-28T16:09:38Z)
• To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions [0.0]
  Large language models (LLMs) are increasingly deployed in agentic frameworks.<n>We develop an agentic system that uses LLMs to iteratively discover differential equations for financial time series.<n>We find that model-informed trading strategies outperform standard LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-11T13:29:32Z)
• Generative Market Equilibrium Models with Stable Adversarial Learning via Reinforcement [10.35300946640037]
  We present a general computational framework for solving continuous-time financial market equilibria under minimal modeling assumptions.<n>Inspired by generative adversarial networks (GANs), our approach employs a novel generative deep reinforcement learning framework.<n>Our algorithm not only learns but also provides testable predictions on how asset returns and volatilities emerge from the endogenous trading behavior of market participants.
  arXiv  Detail & Related papers  (2025-04-05T23:29:46Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• An Auction-based Marketplace for Model Trading in Federated Learning [54.79736037670377]
  Federated learning (FL) is increasingly recognized for its efficacy in training models using locally distributed data. We frame FL as a marketplace of models, where clients act as both buyers and sellers. We propose an auction-based solution to ensure proper pricing based on performance gain.
  arXiv  Detail & Related papers  (2024-02-02T07:25:53Z)
• A Marketplace for Trading AI Models based on Blockchain and Incentives for IoT Data [24.847898465750667]
  An emerging paradigm in Machine Learning (ML) is a federated approach where the learning model is delivered to a group of heterogeneous agents partially, allowing agents to train the model locally with their own data. The problem of valuation of models, as well as the questions of incentives for collaborative training and trading of data/models, have received limited treatment in the literature. In this paper, a new ecosystem of ML model trading over a trusted ML-based network is proposed. The buyer can acquire the model of interest from the ML market, and interested sellers spend local computations on their data to enhance that model's quality
  arXiv  Detail & Related papers  (2021-12-06T08:52:42Z)
• Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting [0.0]
  Model-Free Reinforcement Learning has achieved meaningful results in stable environments but, to this day, it remains problematic in regime changing environments like financial markets. We propose to combine the best of the two techniques by selecting various model-based approaches thanks to Model-Free Deep Reinforcement Learning.
  arXiv  Detail & Related papers  (2021-04-19T19:20:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.