Cite
Notes
Only stored in your browser.
Attribution
Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
arXiv 2026
Aligning VLM Assistants with Personalized Situated Cognition
arXiv 2025
Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute
from 3 papers
Shuyue Hu
Birong Pan
Bocheng Zhou
Chunjiang Mu
Han Qi
Hangfan Zhang
Hankun Kang
Hao Li
Jintao Wen
Lei Bai