MOTOR-Bench supplies a real-world video dataset for structured mental state understanding in learning settings, while MOTOR-MAS improves zero-shot prediction of behavior, cognition, and emotion labels over single models and other multi-agent systems.
Understanding agent scaling in llm-based multi-agent sys- tems via diversity
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.
Multicultural multi-agent LLM systems exhibit substantially lower value diversity than human societies on the World Values Survey, with diversity uncorrelated to per-agent alignment and further reduced by agent interactions.
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
Position paper proposing 'scaling the harness' as the next bottleneck in agentic AI, with three core system challenges and an open-source reference implementation called CheetahClaws.
citing papers explorer
-
MOTOR-Bench: A Real-world Dataset and Multi-agent Framework for Zero-shot Human Mental State Understanding
MOTOR-Bench supplies a real-world video dataset for structured mental state understanding in learning settings, while MOTOR-MAS improves zero-shot prediction of behavior, cognition, and emotion labels over single models and other multi-agent systems.
-
Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.