AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
Reviewed by Pithpith:JPOLYQP2open to challenge →
read the original abstract
Large-language models (LLMs) have demonstrated powerful problem-solving capabilities, in particular when organized in multi-agent systems. However, the advent of such systems also raises several questions on the ability of a complex network of agents to effectively self-organize and collaborate. While measuring performance on standard reasoning benchmarks indicates how well multi-agent systems can solve reasoning tasks, it is unclear whether these systems are able to leverage their topology effectively. Here, we propose AgentsNet, a new benchmark for multi-agent reasoning. By drawing inspiration from classical problems in distributed systems and graph theory, AgentsNet measures the ability of multi-agent systems to collaboratively form strategies for problem-solving, self-organization, and effective communication given a network topology. We evaluate a variety of baseline methods on AgentsNet including homogeneous networks of agents which first have to agree on basic protocols for organization and communication. We find that some frontier LLMs are already demonstrating strong performance for small networks but begin to fall off once the size of the network scales. While existing multi-agent benchmarks cover at most 2-5 agents, AgentsNet is practically unlimited in size and can scale with new generations of LLMs. As such, we also probe frontier models in a setup with up to 100 agents.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
ALEM benchmark reveals LLM agents achieve only ~6% normalized return in open-ended multi-agent settings, with communication as the main driver of coordination and individual task competence not implying coordination c...
-
When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling
DESBench reveals structural trade-offs among centralized, hierarchical, heterarchical, and holonic coordination in dynamic industrial scheduling that outcome metrics alone miss.
-
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
-
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
SAVeR adds self-auditing of internal beliefs in LLM agents via persona-based candidates and constraint-guided repairs, improving faithfulness on six benchmarks without hurting task performance.
-
Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents
Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.