8 citations · 36 across the 21 of their papers we have counts for
Showing cs.MAShow all
2 papers · 1 filter
cs.MA2026
From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration
Ala N. Tak, Teruhisa Misu, Kumar Akash +3
LLM agents are increasingly used for collaborative problem solving and human-group simulation. This makes outcome-only evaluation insufficient: if LLM groups are used as models of…
cs.MA2026
Too Many Specialists: Emergent Inefficiencies and Bottlenecks for Multi-agent Ad-hoc Collaboration
Benjamin Panny, Shashank Mehrotra, Zahra Zahedi +2
Computational models of collaboration without prior coordination often overlook how heterogeneous agent traits and complex task structures jointly produce systemic bottlenecks, ine…