Newest papers

Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents

Mingyang, Chen, Yida, Xu, Huiwen, Chen, Yiming Lu, Wei Jin · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.04040 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los agentes financieros LLM se evalúan a menudo comparando sus retornos de final a final con los de una línea de base y probando la diferencia emparejada contra cero. Esto mide si el despliegue del agente cambia el rendimiento realizado, pero no aisló la habilidad de selección de eventos. Un agente que cambia frecuentemente posiciones de plano a largo puede obtener un retorno emparejado positivo de un grupo de eventos de desplazamiento hacia arriba incluso cuando selecciona eventos aleatoriamente. Proponemos el Auditorio de Valor de la Política del Agente, que mantiene fija la cuenta observada de cada tipo de cambio de acción ordenado y los reasigna aleatoriamente entre eventos elegibles. El salario medio de estas reasignaciones es el punto de referencia de la composición; la diferencia entre el valor de despliegue observado y

Machine translation (Meta M2M100); the English original follows.

Abstract

Financial LLM agents are often evaluated by comparing their end-to-end returns with those of a baseline and testing the paired difference against zero. This measures whether deploying the agent changes realized performance, but it does not isolate event-selection skill. An agent that frequently changes positions from flat to long can earn a positive paired return from an upward-drifting event pool even when it selects events at random. We propose the Agent Policy-Value Audit, which holds fixed the observed count of each ordered action-change type and randomly reassigns them across eligible events. The average payoff from these reassignments is the composition benchmark; the difference between observed deployment value and this benchmark is selection value. In semi-synthetic benchmarks based on real earnings-event returns, a zero-centered paired test falsely attributes passive exposure to selection skill in $11.6\%$ of no-skill replications, while the transition-matched audit reduces this rate to $5.3\%$. Applied retrospectively to 723 earnings events at 44 U.S. consumer-facing firms, the audit decomposes the agent's gross deployment value of $+15.2$ bps/event into a $+25.8$ composition benchmark and a $-10.6$ selection value. The agent does not detectably outperform matched random assignments. Financial-agent evaluations should report deployment value separately from event-selection value.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Benchmark (surveying), Stochastic game, Earnings, Selection (genetic algorithm), Audit, Event (particle physics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange