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.

Hello all,

What have we accomplished in the last month?

– A new Live Strategies reporting section
– Quantpedia Awards 2026 Winners Interview
– 14 new Quantpedia Premium strategies
– 3 new related research papers
– 7 new backtests
– and finally, 8 new posts on our Quantpedia blog

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.

This paper tests whether that rotation in attention leaves a systematic footprint. Using Donchian breakout signals across QQQ and Bitcoin, with cash as a fallback during periods of consolidation, we examine whether investors can harvest momentum without remaining permanently exposed to either asset’s full drawdown profile. The results suggest that the answer is yes: retail attention does not move randomly. It rotates, it concentrates, and—when measured through price breakouts—it can be systematically exploited.

An autonomous research agent replicated nine published US-equity anomalies on clean, survivorship-free data. The question is not only what it found (out-of-sample decay is the rule, and on a faithful build none survive — the lone apparent survivor turned out to be a construction error the discipline caught) but whether you can trust an agent to find it, and the checks that decide the answer.

Factor-based portfolio analysis provides a structured framework for understanding the drivers of investment performance, risk, and long-term behavior. This article applies a set of complementary methods to decompose portfolios into their underlying exposures, evaluate their statistical and economic significance, and assess their behavior across different market regimes.

The analysis is conducted using Quantpedia Pro tools, specifically The Multi Factor Analysis, Factor Analysis Models, The 100-year Portfolio Analysis and The ETF Replication. Together, these methods form a unified factor-based framework that connects decomposition, validation, and replication of portfolio returns. This approach allows for a more robust understanding of portfolio structure and highlights the extent to which observed performance can be explained through systematic factor exposures.