The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
Learning attentional communication for multi-agent coopera- tion.Advances in neural information processing systems, 31
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
A feudal hierarchical MARL method where lower-level policies are rewarded with the upper level's advantage function, with theoretical alignment guarantees and strong benchmark results.
Freezing the graph encoder after the first task reduces forgetting and improves final performance on graph-structured continual multi-agent RL in the new GRAFO benchmark.
SLIM decouples inter-agent communication from policy execution in MARL via a dedicated pathway and a normalized bandwidth budget β, yielding robust performance under tight communication limits on standard benchmarks.
citing papers explorer
-
Why Do Multi-Agent LLM Systems Fail?
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
-
Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning
A feudal hierarchical MARL method where lower-level policies are rewarded with the upper level's advantage function, with theoretical alignment guarantees and strong benchmark results.
-
Continual Graph Multi-Agent Reinforcement Learning
Freezing the graph encoder after the first task reduces forgetting and improves final performance on graph-structured continual multi-agent RL in the new GRAFO benchmark.
-
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
SLIM decouples inter-agent communication from policy execution in MARL via a dedicated pathway and a normalized bandwidth budget β, yielding robust performance under tight communication limits on standard benchmarks.