# Research — 6 papers published on SSRN | AIgen Solutions

> We are part of the academic world and actively publish our research: reinforcement learning for trading, cross-sectional prediction, LLM coding agents, agent memory, on-chain MEV, self-improving mixture-of-experts.

Lingua: en · Pagina: https://aigensolutions.it/en/research · Versione HTML canonica; questo file è il gemello Markdown per lettori automatici.

---

Scientific publications

# We are part of the academic world, and we actively publish our _research._

The strands cover the two axes of our work: **quantitative finance** and **LLM agent engineering**. Every paper is public and verifiable: read, replicate, criticise.

## The six papers

-   01
    
    ### Streamlined Hierarchical Reinforcement Learning for Algorithmic Trading: Architecture Simplification and Empirical Validation
    
    Quant / ML · October 2025 · 42 pp.
    
    [Read on SSRN · 5458097 ↗](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5458097)
    
-   02
    
    ### Feature Scope and Cross-Sectional Return Prediction: Evidence from US Large-Cap Equities
    
    Quant / ML · April 2026 · 98 pp.
    
    [Read on SSRN · 6497598 ↗](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6497598)
    
-   03
    
    ### Conformance, Cost, and Replication in Constrained LLM Coding Agents
    
    LLM agents · May 2026 · 32 pp.
    
    [Read on SSRN · 6751519 ↗](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6751519)
    
-   04
    
    ### Beyond Retrieval vs Context: A Unified Evaluation Framework for External Information Management in LLM Agents
    
    LLM agents · June 2026 · 75 pp.
    
    [Read on SSRN · 6830898 ↗](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6830898)
    
-   05
    
    ### Who Captures Atomic MEV after PBS? Receipt-exact Evidence of Builder Centralization and a Vanishing Independent-searcher Edge on BNB Smart Chain
    
    Blockchain / MEV · July 2026 · 37 pp.
    
    [Read on SSRN · 6926119 ↗](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6926119)
    
-   06
    
    ### FLEX-MoE: Failure-Born Orthogonal Experts for Self-Improving Language Models
    
    LLM agents · July 2026 · 22 pp.
    
    [Read on SSRN · 6978498 ↗](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6978498)
    

[Author profile on SSRN ↗](https://papers.ssrn.com/sol3/cf_dev/AbsByAuth.cfm?per_id=8038244)

Research is not a showcase: **it is the foundation of the method**. The quant papers underpin the platforms; the agent papers underpin agentic-sdlc, the way we deliver software.