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

Indonesian

Agen keuangan LLM sering dievaluasi dengan membandingkan pengembalian end-to-end mereka dengan yang dari garis dasar dan menguji perbedaan berpasangan terhadap nol. Ini mengukur apakah mendistribusikan agen mengubah kinerja yang tercapai, tetapi tidak mengisolasi keterampilan pemilihan acara. Agen yang sering mengubah posisi dari rata-rata ke panjang dapat memperoleh pengembalian berpasangan positif dari pulau peristiwa naik-drifting bahkan ketika ia memilih peristiwa secara acak. Kami mengusulkan Audit Kebijakan-nilai Agen, yang memegang hitungan yang diamati dari setiap jenis laporan perubahan tindakan yang diatur dan secara acak mengalokasikan mereka ke berbagai peristiwa yang memenuhi syarat. Pengembalian rata-rata dari penambahan ulang ini adalah komposisi benchmark; perbedaan antara nilai pemasangan yang diamati dan nilai referensi ini adalah nilai pemilihan. Dalam benchmark semi-

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