@inproceedings{liu-2026-answer,
title = "Answer or Compute? Direct Inference vs. Code Generation for {LLM} Game-State Understanding in {RTS} Games",
author = "Liu, Chang",
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-1.10/",
pages = "133--145",
ISBN = "979-8-89176-485-9",
abstract = "A large language model (LLM) can understand a game state in two ways: answer questions about it directly, or write a program that computes the answer. We compare these modalities on three real-time-strategy tasks{---}factual extraction, strategic assessment, and win prediction{---}holding states, questions, and models fixed. On mechanical questions, code wins decisively: hit-point (HP) aggregation rises from 30{\%} to 100{\%}, and the direct-mode failures are mostly a refusal to declare ties, not bad arithmetic. On judgment tasks, code seemed to win as well, until a trivial baseline exposed why: on snapshots from bot games the material leader always wins, so sign({\ensuremath{\Sigma}}HP) alone scores 100{\%}. On contested states built to remove this artifact, no arm{---}direct, chain-of-thought, or code-based{---}reliably beats chance (40 tests, Holm-corrected), while a simple unit-count cue reaches 72{\%}. Code makes LLMs reliable aggregators; it does not make them judges. We contribute the shortcut audit and hard-set construction that judgment benchmarks built on game traces should adopt."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-2026-answer">
<titleInfo>
<title>Answer or Compute? Direct Inference vs. Code Generation for LLM Game-State Understanding in RTS Games</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Liu</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>A large language model (LLM) can understand a game state in two ways: answer questions about it directly, or write a program that computes the answer. We compare these modalities on three real-time-strategy tasks—factual extraction, strategic assessment, and win prediction—holding states, questions, and models fixed. On mechanical questions, code wins decisively: hit-point (HP) aggregation rises from 30% to 100%, and the direct-mode failures are mostly a refusal to declare ties, not bad arithmetic. On judgment tasks, code seemed to win as well, until a trivial baseline exposed why: on snapshots from bot games the material leader always wins, so sign(\ensuremathΣHP) alone scores 100%. On contested states built to remove this artifact, no arm—direct, chain-of-thought, or code-based—reliably beats chance (40 tests, Holm-corrected), while a simple unit-count cue reaches 72%. Code makes LLMs reliable aggregators; it does not make them judges. We contribute the shortcut audit and hard-set construction that judgment benchmarks built on game traces should adopt.</abstract>
<identifier type="citekey">liu-2026-answer</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.10/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>133</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Answer or Compute? Direct Inference vs. Code Generation for LLM Game-State Understanding in RTS Games
%A Liu, Chang
%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 liu-2026-answer
%X A large language model (LLM) can understand a game state in two ways: answer questions about it directly, or write a program that computes the answer. We compare these modalities on three real-time-strategy tasks—factual extraction, strategic assessment, and win prediction—holding states, questions, and models fixed. On mechanical questions, code wins decisively: hit-point (HP) aggregation rises from 30% to 100%, and the direct-mode failures are mostly a refusal to declare ties, not bad arithmetic. On judgment tasks, code seemed to win as well, until a trivial baseline exposed why: on snapshots from bot games the material leader always wins, so sign(\ensuremathΣHP) alone scores 100%. On contested states built to remove this artifact, no arm—direct, chain-of-thought, or code-based—reliably beats chance (40 tests, Holm-corrected), while a simple unit-count cue reaches 72%. Code makes LLMs reliable aggregators; it does not make them judges. We contribute the shortcut audit and hard-set construction that judgment benchmarks built on game traces should adopt.
%U https://aclanthology.org/2026.realm-1.10/
%P 133-145
Markdown (Informal)
[Answer or Compute? Direct Inference vs. Code Generation for LLM Game-State Understanding in RTS Games](https://aclanthology.org/2026.realm-1.10/) (Liu, REALM 2026)
ACL