@inproceedings{bohojlo-stewart-2026-gains,
title = "Same Gains, Half the Cost: Selector Choice in Automatic Prompt Optimization for Financial Question Answering",
author = "Bohojlo, Cyprian and
Stewart, Christopher M",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.68/",
pages = "1138--1148",
ISBN = "979-8-89176-460-6",
abstract = "Agentic pipelines assign a separately optimized system prompt to each step, so the cost of automatic prompt optimization (APO) multiplies across the pipeline. In this setting, the strategy for selecting candidate prompts cannot ignore budgetary constraints. We study the selection step of a textual gradient APO framework (Pryzant et al., 2023) in financial question answering with retrieval-augmented generation, a domain that stresses both the prompt and the reward signal. We compare the framework{'}s stateless Upper Confidence Bound (UCB) selector against two learned alternatives, PPO and DPO, with BEM as the shared reward. Across 135 experiments spanning three benchmarks, three budgets, and five random seeds, the selectors differ little in average accuracy gain (UCB 13.5{\%} vs. DPO 13.4{\%} vs. PPO 11.2{\%}). Averaging over seeds erases these gaps and cost becomes the differentiating factor. PPO runs in under half the time of UCB (76 vs. 182 minutes per experiment) and its cost stays nearly flat as budget grows. For cost-sensitive deployments, selection has to consider efficiency in addition to accuracy, and PPO emerges as a promising low-cost selector within this APO setup. This design was shaped by an in-progress deployment at a consulting firm that assigns one system prompt to each step of an agentic data-cleaning pipeline."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bohojlo-stewart-2026-gains">
<titleInfo>
<title>Same Gains, Half the Cost: Selector Choice in Automatic Prompt Optimization for Financial Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cyprian</namePart>
<namePart type="family">Bohojlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Stewart</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 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Agentic pipelines assign a separately optimized system prompt to each step, so the cost of automatic prompt optimization (APO) multiplies across the pipeline. In this setting, the strategy for selecting candidate prompts cannot ignore budgetary constraints. We study the selection step of a textual gradient APO framework (Pryzant et al., 2023) in financial question answering with retrieval-augmented generation, a domain that stresses both the prompt and the reward signal. We compare the framework’s stateless Upper Confidence Bound (UCB) selector against two learned alternatives, PPO and DPO, with BEM as the shared reward. Across 135 experiments spanning three benchmarks, three budgets, and five random seeds, the selectors differ little in average accuracy gain (UCB 13.5% vs. DPO 13.4% vs. PPO 11.2%). Averaging over seeds erases these gaps and cost becomes the differentiating factor. PPO runs in under half the time of UCB (76 vs. 182 minutes per experiment) and its cost stays nearly flat as budget grows. For cost-sensitive deployments, selection has to consider efficiency in addition to accuracy, and PPO emerges as a promising low-cost selector within this APO setup. This design was shaped by an in-progress deployment at a consulting firm that assigns one system prompt to each step of an agentic data-cleaning pipeline.</abstract>
<identifier type="citekey">bohojlo-stewart-2026-gains</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.68/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1138</start>
<end>1148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Same Gains, Half the Cost: Selector Choice in Automatic Prompt Optimization for Financial Question Answering
%A Bohojlo, Cyprian
%A Stewart, Christopher M.
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F bohojlo-stewart-2026-gains
%X Agentic pipelines assign a separately optimized system prompt to each step, so the cost of automatic prompt optimization (APO) multiplies across the pipeline. In this setting, the strategy for selecting candidate prompts cannot ignore budgetary constraints. We study the selection step of a textual gradient APO framework (Pryzant et al., 2023) in financial question answering with retrieval-augmented generation, a domain that stresses both the prompt and the reward signal. We compare the framework’s stateless Upper Confidence Bound (UCB) selector against two learned alternatives, PPO and DPO, with BEM as the shared reward. Across 135 experiments spanning three benchmarks, three budgets, and five random seeds, the selectors differ little in average accuracy gain (UCB 13.5% vs. DPO 13.4% vs. PPO 11.2%). Averaging over seeds erases these gaps and cost becomes the differentiating factor. PPO runs in under half the time of UCB (76 vs. 182 minutes per experiment) and its cost stays nearly flat as budget grows. For cost-sensitive deployments, selection has to consider efficiency in addition to accuracy, and PPO emerges as a promising low-cost selector within this APO setup. This design was shaped by an in-progress deployment at a consulting firm that assigns one system prompt to each step of an agentic data-cleaning pipeline.
%U https://aclanthology.org/2026.emnlp-industry.68/
%P 1138-1148
Markdown (Informal)
[Same Gains, Half the Cost: Selector Choice in Automatic Prompt Optimization for Financial Question Answering](https://aclanthology.org/2026.emnlp-industry.68/) (Bohojlo & Stewart, EMNLP 2026)
ACL