作者位次 #3/7ACL 2026Findings· Findings of ACL
When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems
Xin Yang · Junhao Wang · Bintao Tang · Xuxin Cheng · Cao Liu · Ke Zeng · Wenyuan Jiang
摘要
Current LLM-based multi-agent systems remain fragile under scaling, even on algorithmically trivial tasks. We introduce MAS-BENCH, a distributed-sorting benchmark that isolates coordination under explicit communication constraints: each agent observes only a local segment and must collectively pr...