Cite
Notes
Only stored in your browser.
Attribution
Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
two-heads-are-better-than-one-test-time
M3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
arXiv 2025
from 2 papers
Dimitris N. Metaxas
Bangwei Guo
Difei Gu
Hongwu Peng
Ligong Han
Mingyu Zhao
Qixin Zhang
Ruosong Ye
Tong Che
Yang Zhou