@inproceedings{wasmatkar-2026-flight,
title = "Flight to Mediocrity: Why {LLM} Agent Selectors Under-Hire Experts When Quality Claims Are Unverified",
author = "Wasmatkar, Soham",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.31/",
pages = "461--472",
ISBN = "979-8-89176-485-9",
abstract = "AI systems increasingly let one model choose another: an orchestrator routing a task to a sub-agent, or an agent picking a tool from a registry, by self-described ability. What happens when that self-report cannot be checked? In MATCHMARKET, a client hires one of three candidates whose true competence is hidden (2, 5, or 8 of 10), earning the competence of its hire. Candidates are themselves language models, inflating claims under an audit-and-fine incentive. Selectors rarely fall for the loudest liar, picking the inflator only 8{--}15{\%} of the time. They fail by fleeing to mediocrity: 75{--}89{\%} of their mistaken hires land on a safe, moderate candidate, not on the liar. A trivial yardstick makes the cost concrete: believing the highest claim earns 6.72 of a possible 8.0, and no selector we test significantly beats it. The best merely matches it, while the weakest fall significantly below (pooled 5.99, paired p = .002; random scores 5.0). A verified record recovers much of the loss, but only for selectors near chance without it, widening rather than closing cross-model gaps. Every outcome is scored arithmetically, no LLM judge. Unverified capability advertisement behaves like a market for lemons whose cost falls on the honest, capable provider."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wasmatkar-2026-flight">
<titleInfo>
<title>Flight to Mediocrity: Why LLM Agent Selectors Under-Hire Experts When Quality Claims Are Unverified</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soham</namePart>
<namePart type="family">Wasmatkar</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>AI systems increasingly let one model choose another: an orchestrator routing a task to a sub-agent, or an agent picking a tool from a registry, by self-described ability. What happens when that self-report cannot be checked? In MATCHMARKET, a client hires one of three candidates whose true competence is hidden (2, 5, or 8 of 10), earning the competence of its hire. Candidates are themselves language models, inflating claims under an audit-and-fine incentive. Selectors rarely fall for the loudest liar, picking the inflator only 8–15% of the time. They fail by fleeing to mediocrity: 75–89% of their mistaken hires land on a safe, moderate candidate, not on the liar. A trivial yardstick makes the cost concrete: believing the highest claim earns 6.72 of a possible 8.0, and no selector we test significantly beats it. The best merely matches it, while the weakest fall significantly below (pooled 5.99, paired p = .002; random scores 5.0). A verified record recovers much of the loss, but only for selectors near chance without it, widening rather than closing cross-model gaps. Every outcome is scored arithmetically, no LLM judge. Unverified capability advertisement behaves like a market for lemons whose cost falls on the honest, capable provider.</abstract>
<identifier type="citekey">wasmatkar-2026-flight</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.31/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>461</start>
<end>472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Flight to Mediocrity: Why LLM Agent Selectors Under-Hire Experts When Quality Claims Are Unverified
%A Wasmatkar, Soham
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F wasmatkar-2026-flight
%X AI systems increasingly let one model choose another: an orchestrator routing a task to a sub-agent, or an agent picking a tool from a registry, by self-described ability. What happens when that self-report cannot be checked? In MATCHMARKET, a client hires one of three candidates whose true competence is hidden (2, 5, or 8 of 10), earning the competence of its hire. Candidates are themselves language models, inflating claims under an audit-and-fine incentive. Selectors rarely fall for the loudest liar, picking the inflator only 8–15% of the time. They fail by fleeing to mediocrity: 75–89% of their mistaken hires land on a safe, moderate candidate, not on the liar. A trivial yardstick makes the cost concrete: believing the highest claim earns 6.72 of a possible 8.0, and no selector we test significantly beats it. The best merely matches it, while the weakest fall significantly below (pooled 5.99, paired p = .002; random scores 5.0). A verified record recovers much of the loss, but only for selectors near chance without it, widening rather than closing cross-model gaps. Every outcome is scored arithmetically, no LLM judge. Unverified capability advertisement behaves like a market for lemons whose cost falls on the honest, capable provider.
%U https://aclanthology.org/2026.realm-1.31/
%P 461-472
Markdown (Informal)
[Flight to Mediocrity: Why LLM Agent Selectors Under-Hire Experts When Quality Claims Are Unverified](https://aclanthology.org/2026.realm-1.31/) (Wasmatkar, REALM 2026)
ACL