cs.CLNov 6, 2026

Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents

Authors: Yuchen Li, Lisa Liu, Runqi Zou, Shuxuan Kuang, Qingquan Zhang, Julian Togelius

Organizations: Lingnan University · New York University

Abstract

Large language model (LLM) agents coordinate through conversation, and the same message can be phrased in simpler or more complex language, bluntly or politely. We test whether such differences change how other agents judge and act, using the LURK Werewolf framework, which separates each utterance's speech-act predicate from its natural-language realization. We rewrite only the realization, check that the game content is preserved, and replay each game day from saved checkpoints against a re-sampled control. We vary linguistic range consistently across a speaker's messages and politeness strategy per utterance. Across 30 games and 4,335 replays, neither manipulation changes the trust other agents place in the speaker, and no effect on votes or night actions survives correction for multiple comparisons; the largest uncorrected effect is that shifting range away from a neutral paraphrase changes about 4 percentage points more of the other players' votes. In natural play, 88% of face-threatening speech is bald on-record regardless of role.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us

    Mar 27, 2026Maria Milkowski, Tim WeningerDeception in Language ModelsMulti-Agent Communication

  2. Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game

    Jul 30, 2026Niklas Bauer, Lars Benedikt Kaesberg, Akiko Aizawa +3Multi-Agent LLM SystemsSocial Deduction Games

  3. Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?

    May 17, 2026Anvesh Rao Vijjini, Sagar Manjunath, Snigdha Chaturvedi