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 when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive settings along with the cooperative settings. IC3Net controls continuous communication with a gating mechanism and uses individualized rewards foreach agent to gain better performance and scalability while fixing credit assignment issues. Using variety of tasks including StarCraft BroodWars explore and combat scenarios, we show that our network yields improved performance and convergence rates than the baselines as the scale increases. Our results convey that IC3Net agents learn when to communicate based on the scenario and profitability.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
HiComm proposes a plug-in hierarchical communication protocol for cooperative MARL that performs structured information retrieval over observation hierarchies using receiver queries and three-stage decoding, matching or outperforming baselines while reducing volume by up to 23×.
AsynCoMARL is a new asynchronous MARL algorithm that matches leading baselines on success and collision rates while using 26% fewer messages via graph transformers on dynamic communication graphs.
HetNet achieves 5.84% to 707.65% performance gains and 200x bandwidth reduction over baselines in heterogeneous multi-agent robot teams via graph-attention networks and binarized messaging.
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.
A survey that consolidates federated learning, multi-agent algorithms, and collaborative sensing techniques for AI on satellite constellations, including a unifying taxonomy and ongoing GitHub curation.
MASK schedules top-K agents via semantic gating and a global encoder to achieve risk-aware multi-robot coordination that matches unconstrained baselines under bandwidth caps.
PIMbot introduces an adaptive attack using reward-channel and policy manipulation to disrupt cooperation in multi-robot social dilemma RL, shown effective in Gazebo simulation and on NVIDIA Jetson hardware.
Introduces IEI metric and incorporates it into MARL training losses to achieve equivalent task performance with lower message entropy across tested algorithms.
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.
-
HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning
HiComm proposes a plug-in hierarchical communication protocol for cooperative MARL that performs structured information retrieval over observation hierarchies using receiver queries and three-stage decoding, matching or outperforming baselines while reducing volume by up to 23×.
-
Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication
AsynCoMARL is a new asynchronous MARL algorithm that matches leading baselines on success and collision rates while using 26% fewer messages via graph transformers on dynamic communication graphs.
-
Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination
HetNet achieves 5.84% to 707.65% performance gains and 200x bandwidth reduction over baselines in heterogeneous multi-agent robot teams via graph-attention networks and binarized messaging.
-
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.
-
On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellations
A survey that consolidates federated learning, multi-agent algorithms, and collaborative sensing techniques for AI on satellite constellations, including a unifying taxonomy and ongoing GitHub curation.
-
MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics
MASK schedules top-K agents via semantic gating and a global encoder to achieve risk-aware multi-robot coordination that matches unconstrained baselines under bandwidth caps.
-
PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning
PIMbot introduces an adaptive attack using reward-channel and policy manipulation to disrupt cooperation in multi-robot social dilemma RL, shown effective in Gazebo simulation and on NVIDIA Jetson hardware.
-
Learning Multi-Agent Communication Protocol: Study on Information Entropy Efficiency in MARL
Introduces IEI metric and incorporates it into MARL training losses to achieve equivalent task performance with lower message entropy across tested algorithms.