DALA treats inter-agent communication as a centralized auction where agents bid on message value density, yielding SOTA results on seven reasoning benchmarks with far fewer tokens than prior methods.
org/abs/2307.01403
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
GTD generates task-adaptive, sparse communication topologies for multi-LLM agents via guided iterative graph diffusion steered by a proxy model predicting accuracy, utility, and cost.
SCALE-COMM uses contrastive alignment on latent embeddings to decouple and stabilize communication learning from policy optimization in decentralized MARL, showing gains on benchmarks and a warehouse task.
citing papers explorer
-
Cost-Effective Communication: An Auction-based Method for Language Agent Interaction
DALA treats inter-agent communication as a centralized auction where agents bid on message value density, yielding SOTA results on seven reasoning benchmarks with far fewer tokens than prior methods.
-
Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
GTD generates task-adaptive, sparse communication topologies for multi-LLM agents via guided iterative graph diffusion steered by a proxy model predicting accuracy, utility, and cost.
-
SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication
SCALE-COMM uses contrastive alignment on latent embeddings to decouple and stabilize communication learning from policy optimization in decentralized MARL, showing gains on benchmarks and a warehouse task.