Metraipolis › archive › dc_2c186e272cf3
Multi-Agent Debate for Explainable Trading: Reasoning, Consensus, and Performance in Simulated Markets — arXiv:2609.29701
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29701
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:19:52.824Z
- SHA-256 of the archived text
23d3345e81d8ed2b5932fc3219c1e3e7e878738696d6f04da61b968f06605944- Stable URL of this page
https://metraipolis.com/documento/dc_2c186e272cf3
How to cite
Multi-Agent Debate for Explainable Trading: Reasoning, Consensus, and Performance in Simulated Markets — arXiv:2609.29701 — arXiv (en), https://arxiv.org/abs/2609.29701 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c186e272cf3 (Metraipolis archive dc_2c186e272cf3, sha256 23d3345e81d8ed2b5932fc3219c1e3e7e878738696d6f04da61b968f06605944)
BibTeX
@misc{dc2c186e272cf3,
title = {Multi-Agent Debate for Explainable Trading: Reasoning, Consensus, and Performance in Simulated Markets — arXiv:2609.29701},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29701},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c186e272cf3; sha256 23d3345e81d8ed2b5932fc3219c1e3e7e878738696d6f04da61b968f06605944},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29701. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly used for financial decision-making, yet it remains unclear whether improvements in reasoning quality translate into better economic outcomes. We investigate this question using a multi-agent debate framework for portfolio allocation in historical market simulations, where specialized agents propose, critique, and revise investment decisions. Reasoning quality is evaluated across four dimensions: logical validity, evidential support, alternative consideration, and causal alignment, and compared with downstream financial performance. Across 210 controlled runs, aggregate reasoning quality shows no meaningful relationship with Sharpe ratio (r = 0.07, p = 0.29) or total return (r = 0.03, p = 0.70). Structured prompting increases measured reasoning quality from about 0.72 to 0.84 (+17.7%, Cohen's d about 2.0), but these gains do not consistently translate into higher returns. We identify sycophantic convergence as a central failure mode, where agents abandon independent positions during critique-revision cycles and converge toward similar allocations. A Jensen-Shannon divergence intervention that preserves disagreement improves Sharpe by +0.14 (p = 0.028) and Sortino by +0.25 (p = 0.026), while interventions enforcing stronger causal reasoning do not improve financial performance. Our results suggest that multi-agent debate is most valuable when it preserves independent informational signals rather than simply improving measured reasoning quality. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.29701 — 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 2026-10-08T03:50:35.808Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).