Metraipolis › archive › dc_d663d0d3e7fe

Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core — arXiv:2610.30557

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30557
License (as archived)
CC0-1.0
Archived
2026-10-26T01:04:16.790Z
SHA-256 of the archived text
cde064d3265914a0cf5dee71ed0e6363b63f788c98d456b4e62cddf6e00056f9
Stable URL of this page
https://metraipolis.com/documento/dc_d663d0d3e7fe

How to cite

Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core — arXiv:2610.30557 — arXiv (en), https://arxiv.org/abs/2610.30557 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d663d0d3e7fe (Metraipolis archive dc_d663d0d3e7fe, sha256 cde064d3265914a0cf5dee71ed0e6363b63f788c98d456b4e62cddf6e00056f9)
BibTeX
@misc{dcd663d0d3e7fe,
  title = {Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core — arXiv:2610.30557},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30557},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d663d0d3e7fe; sha256 cde064d3265914a0cf5dee71ed0e6363b63f788c98d456b4e62cddf6e00056f9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30557. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Multiagent Systems (cs.MA); Portfolio Management (q-fin.PM).
Pagina del lavoro: https://arxiv.org/abs/2610.30557 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-26T01:03:57.908Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).