MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability (Q7367870)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
No description defined
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability |
No description defined |
Statements
MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability (English)
0 references
3 October 2026
0 references
cs.AI
0 references
Qizhi Chu
0 references
Zekai Yu
0 references
Sijie Wen
0 references
Yang Liu
0 references
Chen Qian
0 references
Cheng Yang
0 references
Chuan Shi
0 references
Zhiyuan Liu
0 references
We introduce MASBench, a multi-agent collaboration benchmark designed under partially observable constraints to systematically evaluate collaboration mechanisms in Large Language Model (LLM)-based Multi-Agent Systems (MAS). It consists of three task categories and provides deterministic evaluation metrics for collaboration outcomes and communication overhead.
0 references
LLM-based Multi-Agent Collaboration
0 references
Partial Observability
0 references
Multi-Agent Benchmark
0 references
1 reference
