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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yang, M., Chen, Yida, Xu, Huiwen, Lu, Y., & Jin, W. (2026). Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents. https://omanscience.com/en/articles/agent-policy-value-audit-separating-transition-composition-from-event-selection-in-financial-llm-agents
MLA 9
Yang, Ming, et al. "Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents." https://omanscience.com/en/articles/agent-policy-value-audit-separating-transition-composition-from-event-selection-in-financial-llm-agents.
Chicago (author–date)
Yang, Ming, Chen, Yida, Xu, Huiwen, Yiming Lu, and Wei Jin. 2026. "Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents." https://omanscience.com/en/articles/agent-policy-value-audit-separating-transition-composition-from-event-selection-in-financial-llm-agents.
Harvard
Yang, M., Chen, Yida, Xu, Huiwen, Lu, Y. and Jin, W. (2026) 'Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents', Available at: https://omanscience.com/en/articles/agent-policy-value-audit-separating-transition-composition-from-event-selection-in-financial-llm-agents.
Vancouver
Yang M, Chen, Yida, Xu, Huiwen, Lu Y, et al. Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents. https://omanscience.com/en/articles/agent-policy-value-audit-separating-transition-composition-from-event-selection-in-financial-llm-agents
IEEE
M. Yang, Chen, Yida, Xu, Huiwen, Y. Lu, and W. Jin, "Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents," https://omanscience.com/en/articles/agent-policy-value-audit-separating-transition-composition-from-event-selection-in-financial-llm-agents.