computer-use benchmarking 1coordination 1interactive agents 1large language models 1long-horizon tasks 1multi-agent exploration 1partial observability 1peer selection 1safety auditing 1tool-use evaluation 1
From the 2 of 8 linked papers with an AI index.
Showing cs.MAShow all
2 papers · 1 filter
cs.MA2026
Multi-Agent LLMs Fail to Explore Each Other
Hyeong Kyu Choi, Jiatong Li, Wendi Li +2
The paper shows that large language model agents struggle to explore each other in multi-agent settings, leading to poor coordination, and introduces the MACE framework that uses s…
cs.MA2025
Self-Resource Allocation in Multi-Agent LLM Systems
Alfonso Amayuelas, Jingbo Yang, Saaket Agashe +4
With the development of LLMs as agents, there is a growing interest in connecting multiple agents into multi-agent systems to solve tasks concurrently, focusing on their role in ta…