Skip to content
conftrace_
2024 ICML ICML 2024

MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Justin Chen, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal

Topics

Artificial Intelligence > Core AI > Multi-Agent Systems Machine Learning > Core Methods > Representation Learning Artificial Intelligence > Core AI > Reasoning

Keywords

contrastive loss graph encoder smaller language model self consistency distillation multi-agent interaction graphs
Download PDF