LLM

The integration of artificial intelligence into algorithmic trading has ignited a race to transform generative text into systematic alpha. A new paper written by Steven Edwards empirically investigates whether constructing a synthetic consensus using large language models can simulate information aggregation dynamics or if it merely acts as a sophisticated echo chamber. By utilizing an expansive framework to evaluate portfolio construction across distinct synthetic mandates, the study challenges whether generative agents can truly democratize the wisdom of crowds within highly efficient capital markets.

Large language models are already capable of summarizing financial research, but are they ready to conduct it? In their latest paper, researchers from Google, Boston College, and Columbia introduce a framework where a large language model doesn’t just fetch data—it acts as an autonomous AI research agent capable of navigating the “hypothesis discovery loop.” By placing an LLM within a human-designed laboratory—complete with a symbolic language of 66 accounting primitives and a standardized backtesting pipeline—the authors tested whether AI can move beyond black-box predictions to generate economically legible and statistically robust signals. This isn’t just about throwing a transformer at a price series; it is a systematic attempt to automate the “propose–test–reflect” cycle that defines empirical finance.

Investors often face a simple but important problem. They receive a fund equity curve, a strategy track record, or a portfolio performance series, but they do not know what is actually inside. The manager may provide only a broad description, while the realized return stream may in practice be driven by a mix of momentum, tactical allocation, defensive overlays, cross-asset rotation, or other systematic effects.

In this test, the unknown equity curve was treated as a blind case. The “correct” answer was not used during the analysis. The task was therefore not to confirm a known decomposition, but to test whether an API-based workflow can identify which known systematic strategies best explain the behavior of a black-box curve.

Quantitative investors usually start their research by analyzing individual trading strategies. They compare performance, risk, implementation complexity, market exposure, and the economic intuition behind each anomaly. However, once historical equity curves of individual strategies are available, a different research question becomes possible. Instead of asking only which individual strategy looks attractive, we can ask how to allocate capital across a broad universe of strategies.

The Quantpedia API makes this type of analysis practical. It provides access not only to strategy metadata, but also to historical strategy equity curves. Therefore, users can move from strategy discovery to systematic strategy portfolio construction.

Artificial intelligence is gradually changing the way quantitative researchers interact with financial data. Instead of manually browsing databases, comparing strategies one by one and filtering spreadsheets, modern research workflows increasingly rely on conversational systems capable of retrieving and summarizing structured information automatically.

One practical application is combining the Quantpedia API with an LLM such as ChatGPT, Claude or Cursor AI to create a lightweight quant research assistant. In this setup, Quantpedia API provides structured access to quantitative trading strategies, performance metrics, classifications, equity curves, trading codes, and related research metadata through the official Quantpedia API, while the LLM acts as a conv

One year ago, in our article “Can We Finally Use ChatGPT as a Quantitative Analyst?”, we explored the feasibility of leveraging ChatGPT for quantitative analysis. Since then, a lot has changed: newer models are now available (from OpenAI and also other vendors), and the ecosystem around AI-assisted analysis has evolved significantly. Back then, we encountered numerous challenges, ranging from model hallucinations and faulty code generation to excessive overfitting. In this article, we revisit these issues to assess what has improved and what remains unresolved, with the goal of finally answering whether we can use LLMs to assist with quantitative analysis tasks.