AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that searches over frozen research artifacts---hypotheses, executable expressions, platform evidence, rationales, and review status---rather than formulas alone. To our knowledge, AgonAlpha is the first alpha-mining system to combine verified artifact search, a fresh-context adversarial reviewer with re-execution and veto authority, and pending-aware parallel budget allocation, together with a complete public evidence trail. Independent deployments on WorldQuant BRAIN produced SPECTACULAR-grade alphas across five users and six model backends, with Fitness reaching 9.50 and Sharpe reaching 3.48, while retaining prompt-to-expression provenance for every submission.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 18 of its 35 references that are in the map. First posted on arXiv 4 Aug 2026.
Builds on
18 of 35 references.
References · 18
- 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 688
- 2015Non-stochastic Best Arm Identification and Hyperparameter Optimizationcited by 219
- 2023Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investmentcited by 54
- 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimizationcited by 39
- 2024LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Predictioncited by 31
- 2024AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factorscited by 25
- 2018Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Searchcited by 13
- 2024QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCEcited by 13
- 2025Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Miningcited by 13
- 2026FactorMiner: A Self-Evolving Agent with Skills and Experience Memory for Financial Alpha Discoverycited by 13
- 2025Cognitive Alpha Mining via LLM-Driven Code-Based Evolutioncited by 12
- 2026QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Miningcited by 12
6 more
- 2025ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordinationcited by 7
- 2026PerspectiveGap: A Benchmark for Multi-Agent Orchestration Promptingcited by 6
- 2026AlphaLogics: A Market Logic-Driven Multi-Agent System for Scalable and Interpretable Alpha Factor Generationcited by 4
- 2026From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discoverycited by 4
- 2026Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economycited by 4
- 2026AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolutioncited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
- 2026AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents
- 2026EPOCH: Reliable Discovery through Evidence-Governed Search
- 2025AlphaResearch: Accelerating New Algorithm Discovery with Language Models
- 2026AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative Investment
- 2026AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining
- 2025AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay
- 2026Argus: Evidence Assembly for Scalable Deep Research Agents