AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

CSP4SDG: Constraint and Information-Theory Based Role Identification in Social Deduction Games with LLM-Enhanced Inference

Kaijie Xu, Fandi Meng, Clark Verbrugge, Simon Mark Lucas

AAAI 2026 · Multi-agent systems and games › Games and equilibria · approach: Learning with strategic agents · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add assertions as high-weight soft constraints to Strict (ablation)CSP4SDG · Avalon-NLU objectivemarginal accuracy: 0.28 -> 0.33Improved
add IG-weighted hypotheses on top of assertions (ablation)CSP4SDG · Avalon-NLU objectivemarginal accuracy: 0.33 -> 0.34Improved
IG hypothesis weights instead of manual weights (ablation)CSP4SDG · Avalon-NLU objectivemarginal accuracy: 0.34 vs 0.33No clear effect
add soft constraints (hypotheses) to Strict (ablation)CSP4SDG · Mafia-UCB objectivemarginal accuracy: marginal 0.70 -> 0.73; MAP 0.90 -> 0.76Mixed
scaling all hypothesis weights by 0.25 to 4 (ablation)CSP4SDG · Avalon-NLU / MafiaMAP accuracy: MAP change <= 1.5 ppNo clear effect
add CSP posteriors to the LLM prompt (ablation)LLM (GPT-4o-mini) · Avalon-NLU objectivemarginal accuracy: 0.14 -> 0.19Improved
add CSP posteriors to the LLM prompt (ablation)LLM (GPT-4o-mini) · Mafia-UCB objectivemarginal accuracy: GChat 0.56 -> 0.69; TChat 0.66 -> 0.69Mixed
use turn-based chat instead of global chatLLM · Mafia-UCB objectivemarginal accuracy: 0.56 -> 0.66Improved
use a stronger LLM backbone (GPT-4o-mini to GPT-4.1 / DeepSeek-v3) (ablation)LLM-only · Avalon-NLU objectivemarginal accuracy: 0.14 -> 0.15 / 0.16No clear effect
use CSP+HypIG instead of LLM-only on AvalonLogs 9-playerCSP vs LLM · AvalonLogs 9-player objectivemarginal accuracy: 0.280 -> 0.360Improved
feed CSP posteriors to LLM on AvalonLogs (ablation)LLM+CSP · AvalonLogs 6-player objectivemarginal accuracy: 0.289 vs CSP Strict 0.290No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy