arXiv q-fin· Yebo Feng, Jingyang Dai, Liangrui Pan, Nelson Lau, Jiahua Xu, Yang Liu·· 5 hr agoAI Score55
arXiv paper proposes Steward, a multi-agent LLM autonomous investment system with an invariant core
Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core
AI summary
This paper proposes Steward, a multi-agent LLM autonomous investment system that defines self-evolution boundaries through a type system. Its core includes nine types of role-specialized agents, seven layers of shared memory, and a verifiable quarterly reflective self-evolution mechanism, all operating around an immutable core that cannot be self-edited.
Source:arXiv q-fin · arxiv.org
Academic papers#Papers / Research#Large Language Model Applications#Machine Learning#Portfolio Construction#Risk Management#arXiv