Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
Enhance reasoning for large language models in the game werewolf
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 6polarities
background 2representative citing papers
Hybrid Bayesian-graph LLM agent reaches competitive performance against large models and achieves 67% win rate against humans in controlled Avalon play, outperforming baselines and human teammates.
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
SOM uses a Structural Causal Model to create an explicit graph of opponent observation-to-action links, allowing LLMs to reason along those paths for more accurate and stable predictions in multi-agent settings.
citing papers explorer
-
Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia
Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
-
Bayesian Social Deduction with Graph-Informed Language Models
Hybrid Bayesian-graph LLM agent reaches competitive performance against large models and achieves 67% win rate against humans in controlled Avalon play, outperforming baselines and human teammates.
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse
The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.
-
SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal Model
SOM uses a Structural Causal Model to create an explicit graph of opponent observation-to-action links, allowing LLMs to reason along those paths for more accurate and stable predictions in multi-agent settings.