quantitative investment teams

Abstract: LLM agents that act on live Web data must combine heterogeneous evidence, remember what they have done and improve from outcomes without weakening their own safeguards. We study this problem in autonomous investing, where every action is irreversible and based on untrusted Web content. We present Steward, a multi-agent LLM system that draws the boundary of self-evolution in its type system. First, nine role-specialised agents decide jointly: four analysts read news feeds, SEC filings, macroeconomic series and market data and emit typed reports, from which a Portfolio Manager sets target positions that a protected Risk Manager audits. Second, a seven-layer shared memory, assembled by code from the system's own record, gives each decision its position context, the market narrative, calibration and the agent's past decisions. Third, the system improves itself by review: code grades every trade and forecast nightly and writes the grades into memory, and each quarter a reflector proposes prompt learnings that a deterministic gate applies reversibly and replay of recorded inputs verifies. All three operate around an invariant core of order arithmetic, risk rules and discipline-agent prompts that no self-edit can reach. In a five-month live deployment (102 trading days, 1,632 LLM calls), the system contained a 24.6% sector drawdown to a 0.3% loss; in replay of its recorded inputs, a single model given the same raw data traded more and lost 1.35 points against the market over five days where the joint design showed no significant loss, and no injected instruction was followed; and a 2015-2026 backtest shows the core alone lowering the maximum drawdown under all 50 random entry policies. The reflector traced the dominant failure to its root cause, and the gate applied a learning that the agent adopted on trigger evenings and on no control evening. Code: https://github.com/yebof/quant-agent

Abstract: Reliable evaluation of LLM-based alpha mining requires more than positive backtest summaries. We audit a preserved project at three levels: historical run counters, outcome retention, and a separately scoped public reanalysis. Three historical runs report 67, 20, and 11 keep decisions, but the comparison mixes metric populations: a mean over kept candidates is compared with a mean of per-round maxima, and successful evaluations with all returned outcomes. These artifacts cannot identify an architecture advantage. A released 1,837-expression catalog also excludes non-positive OOS outcomes, making its zero-reversal rate non-informative. We then account for all 1,047 unique expressions in a frozen, IS-screened preserved pool using forty A-shares and 2024-2025 rank associations. A versioned public-operator correction yields 923 scorable records, 99 with insufficient valid dates, and 25 unsupported, without modifying the other 990 prior diagnostics. Among scorable records, 671 have positive and 252 negative signed mean rank-IC. Simple untrained references also show positive associations, so this distribution does not establish incremental agent skill or profitability. The case study motivates explicit metric grains, immutable cohort accounting, and provenance-aware interpretation rather than architectural rankings from incomplete records.

Abstract: Language models that read financial news are usually trained on text from the same years used to test them, so a backtest can reward hindsight. We build news topics from NoLBERT, an encoder pretrained only on text published between 1976 and 1995, adapted into a sentence encoder by contrastive fine-tuning on passages of the same article, with no labels or returns. We compare it with LDA, MiniLM and FinBERT readers on 1.26 million articles from 2012 to 2024, convert each reader's topics into attention shocks and stock exposures, and forecast the returns of the 1,000 largest US stocks with eight models at three rebalancing frequencies. Models are fitted on 2013-2019, choices are made on 2020-2021, and 2022-2024 is held out. The experiment with the best validation score loses money at every frequency. Measuring attention shocks against the past 63 trading days instead of 5 raises the test rank IC of every reader. NoLBERT gives the most stable topics and forecasts about as well as LDA. An equal-weight combination of all readers and models earns a monthly net Sharpe ratio of 1.12, significant against zero before adjusting for the search but not against a price-only benchmark.

Abstract: Formulaic alpha mining seeks interpretable expressions that rank assets by future returns. The task is challenging because it demands simultaneous processing of unstructured market descriptions, historical data, and quantitative evaluation of candidate factors, yet most existing methods exploit only a subset of these signals. We introduce AlphaPilot, a reinforcement-learning framework that trains multi-turn tool-using LLM agents for adaptive alpha mining. The agent conditions on market descriptions, proposes factor expressions, queries real-data evaluator feedback, and updates a retained factor pool across turns. This design jointly leverages market text, LLM financial knowledge, real data, and evaluation feedback. At inference time, AlphaPilot performs day-by-day search and pool updates to adapt to shifting market regimes. Across three independent runs in out-of-sample rolling backtests on CSI300 and CSI500, AlphaPilot achieves mean total returns of 42.93% and 54.19%, with mean Sharpe ratios of 2.46 and 2.86, respectively. It attains the highest mean total return, Sharpe, and RankIC among the evaluated methods on both universes.

Abstract: If seven AI advisors give similar forecasts, should we trust them more? Agreement can indicate useful shared evidence, but it can also reflect an asset that was easier to forecast in the first place. We examine this distinction using 928 completed first-quarter forecasts for 232 assets across four production batches of iPulse AI. Ten historical Gemini configurations are grouped into seven investment frameworks; their archived forecasts are compared with later market outcomes, without generating new reports. Mean absolute return error rises from 10.31 percentage points in the lowest-disagreement quartile to 21.05 in the highest. Yet a forecast of no price change shows almost the same increase, from 9.89 to 21.15. The relationship between disagreement and additional forecast error is not resolved after accounting for visible asset risk. Retaining the quarter of forecasts with lowest historical volatility produces lower error than retaining those with least disagreement: 7.97 versus 10.31 percentage points. Agreement about direction behaves differently. When at least six of seven frameworks share a direction, directional accuracy is higher, but return-magnitude error is also larger. These results distinguish three questions often collapsed into one confidence score: how risky the asset is, whether advisors agree on its direction, and how precisely they forecast its return. For this historical council, agreement is informative in specific ways; it is not a general certificate of forecast reliability.