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.
arXiv preprint arXiv:2412.19726 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Dialogue between partially-observing LLM agents cuts action conflicts by 40-83 points but lowers task success versus silent coordination, with new metrics exposing limited genuine world-model alignment.
citing papers explorer
-
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.
-
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
Dialogue between partially-observing LLM agents cuts action conflicts by 40-83 points but lowers task success versus silent coordination, with new metrics exposing limited genuine world-model alignment.
- DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories