# AQuA: Recursively Self-Improving Quantitative Trading Research Agents

arXiv: https://arxiv.org/abs/2608.12841 · HTML: https://mlsanity.com/paper/2608.12841/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 39 of its 66 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [xLSTM: Extended Long Short-Term Memory](https://mlsanity.com/paper/2405.04517/) (2024)
- [Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models](https://mlsanity.com/paper/2406.10162/) (2024)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [The Ladder: A Reliable Leaderboard for Machine Learning Competitions](https://mlsanity.com/paper/1502.04585/) (2015)
- [FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction](https://mlsanity.com/paper/2508.11987/) (2025)
- [AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay](https://mlsanity.com/paper/2502.16789/) (2025)
- [GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators](https://mlsanity.com/paper/2512.19682/) (2025)
- [Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning](https://mlsanity.com/paper/2306.12964/) (2023)
- [AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment](https://mlsanity.com/paper/2103.16196/) (2021)
- [AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes](https://mlsanity.com/paper/2506.14728/) (2025)
- [FactorMiner: A Self-Evolving Agent with Skills and Experience Memory for Financial Alpha Discovery](https://mlsanity.com/paper/2602.14670/) (2026)
- [QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining](https://mlsanity.com/paper/2602.07085/) (2026)
- [Cognitive Alpha Mining via LLM-Driven Code-Based Evolution](https://mlsanity.com/paper/2511.18850/) (2025)
- [QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCE](https://mlsanity.com/paper/2409.05144/) (2024)
- [Alita-G: Self-Evolving Generative Agent for Agent Generation](https://mlsanity.com/paper/2510.23601/) (2025)
- [RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents](https://mlsanity.com/paper/2603.11337/) (2026)
- [Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading](https://mlsanity.com/paper/2508.06312/) (2025)
- [FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains](https://mlsanity.com/paper/2601.12259/) (2026)
- [Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks](https://mlsanity.com/paper/2602.23330/) (2026)
- [From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery](https://mlsanity.com/paper/2605.15412/) (2026)
- [EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery](https://mlsanity.com/paper/2606.13662/) (2026)
- [Learning from Expert Factors: Trajectory-level Reward Shaping for Formulaic Alpha Mining](https://mlsanity.com/paper/2507.20263/) (2025)
- [CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency](https://mlsanity.com/paper/2512.00417/) (2025)
- [AlphaLogics: A Market Logic-Driven Multi-Agent System for Scalable and Interpretable Alpha Factor Generation](https://mlsanity.com/paper/2603.20247/) (2026)

## Built on by (most cited first, 3 of 3)

- [AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining](https://mlsanity.com/paper/2609.29014/) (2026)
- [iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model](https://mlsanity.com/paper/2609.29626/) (2026)
- [SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm](https://mlsanity.com/paper/2610.20431/) (2026)

## Abstract (arXiv)

We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve the hypotheses and candidates proposed in later iterations. We present AQuA, which comprises two separate language-model-driven research systems: one for symbolic factor discovery and one for trainable model development. Each system records experimental results and uses them to guide subsequent proposals. Each operates in a fixed sandbox, which fixes the data splits, feature and label definitions, and evaluator while allowing the model to act only through constrained factor expressions or configuration diffs. The factor system, a manager-mediated multi-agent pipeline, discovers and combines factors into a signal that reaches a combined validation information coefficient of about 0.190 on a crypto universe. The model system, a config-driven loop over a hybrid time-series architecture, reaches a per-stock information coefficient of +0.0843 on US equities and converts it into a threshold long/short strategy with a held-out Sharpe of up to +2.50 at a two-leg cost. The strategy is positive in every year from 2021 to 2025.