Metraipolis › archive › dc_584abfe73a49
OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents — arXiv:2608.09988
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09988
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:14:25.888Z
- SHA-256 of the archived text
6842c7660ffde8de48e584befda89c5b070f26461abacc52b568fb56d1dde78c- Stable URL of this page
https://metraipolis.com/documento/dc_584abfe73a49
How to cite
OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents — arXiv:2608.09988 — arXiv (en), https://arxiv.org/abs/2608.09988 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_584abfe73a49 (Metraipolis archive dc_584abfe73a49, sha256 6842c7660ffde8de48e584befda89c5b070f26461abacc52b568fb56d1dde78c)
BibTeX
@misc{dc584abfe73a49,
title = {OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents — arXiv:2608.09988},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09988},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_584abfe73a49; sha256 6842c7660ffde8de48e584befda89c5b070f26461abacc52b568fb56d1dde78c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09988. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are increasingly used to read markets, assess risk, and allocate capital. However, reported results for LLM trading agents can be inflated by look-ahead leakage, optimistic execution, and risk mandates that are described but not enforced. We present OpenPM, an auditable point-in-time evaluation framework for LLM portfolio-management agents. In OpenPM, an agent manages a \$1M long-only book over the S\&P 500 universe using market data at five-minute intervals. Every record visible to the agent must be available at the decision time. Natural-language risk mandates are converted into typed constraints and enforced on the executed portfolio. Each run produces audit artifacts, including a contamination certificate, a cost-sensitivity curve, and a constraint-adherence report. We also build a reference agent named the tiered allocator, where typed analysts score candidates, a constructor LLM proposes weights, and a deterministic critic guarantees feasibility. We isolate constructor behavior by capturing analyst evidence once and replaying it across constructor models. In our short-window case study, stronger constructors show modest and model-dependent gains over equal weighting on the same pool, but analyst quality matters more than constructor choice, and turnover is the main cost driver. All returns are upper bounds on a single frozen window without market impact, not validated alpha. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CL). Categorie arXiv: Computational Engineering, Finance, and Science (cs.CE) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.09988 — 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 2026-10-19T06:08:50.349Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).