REVIEW 9 cited by
Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf. In Werewolf Arena, LLMs compete against each other, navigating the game's complex dynamics of deception, deduction, and persuasion. The framework introduces a dynamic turn-taking system based on bidding, mirroring real-world discussions where individuals strategically choose when to speak. We demonstrate the framework's utility through an arena-style tournament featuring Gemini and GPT models. Our results reveal distinct strengths and weaknesses in the models' strategic reasoning and communication. These findings highlight Werewolf Arena's potential as a challenging and scalable LLM benchmark.
Forward citations
Cited by 9 Pith papers
-
MafiaScope: Non-Invasive, Time-Resolved Belief Probing for LLM Agents in Social Deduction Games
Non-invasive per-utterance belief probes in Mafia, auto-scored against engine truth, expose poorly calibrated LLM confidence and 1.5× over-prediction of being suspected.
-
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
Changing one LLM agent's secret objective in Werewolf lowers its team's win rate and changes its reasoning, while its public chat stays deceptively normal.
-
Auditing Belief-Conditioned LLM Agents in Hidden-Information Social Deduction Games
An external belief audit framework for LLM Werewolf agents associates active belief with higher good-side win rates while exposing low action-belief consistency and rejecting forced consumption.
-
Strategy Adaptation in Large Language Model Werewolf Agents
Dynamically switching between Support and Attack strategies based on role estimates raises win rates for Werewolf LLM agents, with mixed effects for Villagers.
-
SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models
SocialMaze is a six-task benchmark that claims to evaluate LLM social reasoning along deep reasoning, dynamic interaction, and information uncertainty dimensions.
-
Cumulative suspicion and absorption dynamics in an agent-based Mafia game
History-dependent suspicion scores in an agent Mafia model yield F(τ)∼(τ/N)^{N_m} early extinction without detectives and an empirical N_c collapse of win probabilities that detectives break.
-
TextAtari: 100K Frames Game Playing with Language Agents
TextAtari is a text-based Atari benchmark for language agents; 7-8B LLMs stay below 10% of human scores in over 90% of tested conditions, and knowledge injection helps more than chain-of-thought.
-
Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets
AI agents in future labor markets will need metacognitive and strategic reasoning because incomplete information creates adverse selection, moral hazard, and reputation effects.
-
Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers
A taxonomy-based survey of bidirectional game theory and LLM research, spanning evaluation, alignment, economic competition, and LLM-driven game solving.
Discussion (0). Continue with ORCID to comment.