Author name: Zhanzhi Lou, Hui Chen, Yibo Li, Qian Wang, Bryan Hooi

arXiv:2604.00830v2 Announce Type: replace
Abstract: Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation poli…

arXiv:2604.00830v1 Announce Type: cross
Abstract: Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy…