MECoBench is a benchmark showing that multimodal agent collaboration improves embodied task performance when communication balances coordination costs, with gains also under noisy conditions.
V illager A gent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in M inecraft
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.MA 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
GBC treats multi-agent LLM workflows as differentiable graphs to enable token-level attribution and targeted optimization, with reported gains on MultiWOZ and τ-bench.
citing papers explorer
-
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
MECoBench is a benchmark showing that multimodal agent collaboration improves embodied task performance when communication balances coordination costs, with gains also under noisy conditions.
-
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
GBC treats multi-agent LLM workflows as differentiable graphs to enable token-level attribution and targeted optimization, with reported gains on MultiWOZ and τ-bench.