OpenAlex ·
Multi-Agent Debate for Explainable Trading: Reasoning, Consensus, and Performance in Simulated Markets
- Published
- Source
- OpenAlex
- Published in
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2609.29701
- Original
- Read it at the publisher
- Topics
Abstract
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.
The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.
Read it on ReadSearch
Each opens after you create an account, and brings you back to this paper.
More in Artificial Intelligence
Metaorder modelling and identification from public data
Nonparametric inference for density-dependent McKean--Vlasov diffusions
End-to-End Neural Shrinkage of Indefinite Pairwise Correlation Matrices for Small-Cap-Inclusive Portfolios
Illiquidity at Risk
Two Kinds of Nothing: What Insignificant Results in Finance Actually Show
Get the few papers worth your time in Artificial Intelligence every morning.
ReadSearch reads the new papers in your field each day and brings you the few worth reading, each with its key finding in a sentence.