3 papers
cs.AI2026
Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems
Jianxin Gao, Runze Li, Tianyi Yu +3
Multi-agent systems built on large language models (LLMs) restate observations as a matter of course: relays forward them, shared boards repeat them and discussion rounds echo them…
cs.AI2026
Interchangeable in Role, Not in History: Replacing Members of Formed LLM Teams
Jianxin Gao, Tianyi Yu, Linna Deng +4
Multiagent LLM systems often treat a role as a slot: when a member is replaced, any agent competent at the role is expected to fill it. We test this view on teams whose members kee…
cs.AI2026
MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft
Jianxin Gao, Beini Hu, Runze Li +7
With the rapid progress of large language models (LLMs), an interesting question has emerged: how do LLM-based agents perform in Minecraft? To date, most Minecraft benchmarks evalu…