@inproceedings{zou-etal-2026-finevo,
title = "{F}in{E}vo: Financial Language Agents Shape the Markets That Evaluate Them",
author = "Zou, Mingxi and
Chen, Jiaxiang and
Liang, Langzhang and
Wang, Zhuo and
Luo, Aotian and
Zhang, Chi and
Sun, Danny Dongning and
Xu, Zenglin",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.5/",
pages = "31--52",
ISBN = "979-8-89176-466-8",
abstract = "Financial language agents are commonly evaluated through static prediction tasks or isolated historical backtests, where an agent{'}s decisions cannot affect subsequent prices or the behavior of competing strategies. This overlooks a defining property of real markets: interpretations of financial news influence order flow, price formation, and the competitive environment faced by other participants. We introduce FINEVO, a closed-loop evaluation framework that integrates time-stamped financial news, heterogeneous trading agents, a continuous double-auction market, and population-level capital reallocation. FINEVO evaluates language-based agents alongside technical, forecasting, reinforcement-learning, and informed strategies, reporting not only returns but also market concentration, strategic reorganization, regime-dependent standing, and recovery from shocks. Across 128-run suites of controlled market shocks and historical-news-conditioned episodes, we find that language-agent performance is strongly contingent on the surrounding market regime and agent population. Endogenous price formation also causes identical information schedules to produce different outcomes under different competitive compositions. Mechanism ablations further show that innovation is critical for maintaining contestability: removing it increases mean HHI from 0.189 to 0.477 and mean Top-1 capital share from 0.344 to 0.531. These results suggest that financial language agents should be evaluated not only by how accurately they interpret information, but also by how their decisions reshape the markets in which they operate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zou-etal-2026-finevo">
<titleInfo>
<title>FinEvo: Financial Language Agents Shape the Markets That Evaluate Them</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxi</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Langzhang</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aotian</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danny</namePart>
<namePart type="given">Dongning</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zenglin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>Financial language agents are commonly evaluated through static prediction tasks or isolated historical backtests, where an agent’s decisions cannot affect subsequent prices or the behavior of competing strategies. This overlooks a defining property of real markets: interpretations of financial news influence order flow, price formation, and the competitive environment faced by other participants. We introduce FINEVO, a closed-loop evaluation framework that integrates time-stamped financial news, heterogeneous trading agents, a continuous double-auction market, and population-level capital reallocation. FINEVO evaluates language-based agents alongside technical, forecasting, reinforcement-learning, and informed strategies, reporting not only returns but also market concentration, strategic reorganization, regime-dependent standing, and recovery from shocks. Across 128-run suites of controlled market shocks and historical-news-conditioned episodes, we find that language-agent performance is strongly contingent on the surrounding market regime and agent population. Endogenous price formation also causes identical information schedules to produce different outcomes under different competitive compositions. Mechanism ablations further show that innovation is critical for maintaining contestability: removing it increases mean HHI from 0.189 to 0.477 and mean Top-1 capital share from 0.344 to 0.531. These results suggest that financial language agents should be evaluated not only by how accurately they interpret information, but also by how their decisions reshape the markets in which they operate.</abstract>
<identifier type="citekey">zou-etal-2026-finevo</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.5/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>31</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FinEvo: Financial Language Agents Shape the Markets That Evaluate Them
%A Zou, Mingxi
%A Chen, Jiaxiang
%A Liang, Langzhang
%A Wang, Zhuo
%A Luo, Aotian
%A Zhang, Chi
%A Sun, Danny Dongning
%A Xu, Zenglin
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F zou-etal-2026-finevo
%X Financial language agents are commonly evaluated through static prediction tasks or isolated historical backtests, where an agent’s decisions cannot affect subsequent prices or the behavior of competing strategies. This overlooks a defining property of real markets: interpretations of financial news influence order flow, price formation, and the competitive environment faced by other participants. We introduce FINEVO, a closed-loop evaluation framework that integrates time-stamped financial news, heterogeneous trading agents, a continuous double-auction market, and population-level capital reallocation. FINEVO evaluates language-based agents alongside technical, forecasting, reinforcement-learning, and informed strategies, reporting not only returns but also market concentration, strategic reorganization, regime-dependent standing, and recovery from shocks. Across 128-run suites of controlled market shocks and historical-news-conditioned episodes, we find that language-agent performance is strongly contingent on the surrounding market regime and agent population. Endogenous price formation also causes identical information schedules to produce different outcomes under different competitive compositions. Mechanism ablations further show that innovation is critical for maintaining contestability: removing it increases mean HHI from 0.189 to 0.477 and mean Top-1 capital share from 0.344 to 0.531. These results suggest that financial language agents should be evaluated not only by how accurately they interpret information, but also by how their decisions reshape the markets in which they operate.
%U https://aclanthology.org/2026.finnlp-1.5/
%P 31-52
Markdown (Informal)
[FinEvo: Financial Language Agents Shape the Markets That Evaluate Them](https://aclanthology.org/2026.finnlp-1.5/) (Zou et al., FinNLP 2026)
ACL
- Mingxi Zou, Jiaxiang Chen, Langzhang Liang, Zhuo Wang, Aotian Luo, Chi Zhang, Danny Dongning Sun, and Zenglin Xu. 2026. FinEvo: Financial Language Agents Shape the Markets That Evaluate Them. In Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing, pages 31–52, Budapest, Hungary. Association for Computational Linguistics.