arXiv 2610.27628 · cs.CL · 2026-10-20
PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
Pan Wang, Yihao Hu, Guangyuan Dong, Yitong Lin, Hang Wang, Zimi Liu, Zhihao Wen, Jianshe Li and 3 more
ant-international
In latest · #214 Added on 2026-10-22
One-line takeaway
PAR aligns each loop iteration of a looped LM with task progress and anchors state norms, extrapolating state tracking to 16x training length.
PAR 让循环语言模型每轮迭代对齐“已完成的步数”并锚定状态范数，状态追踪任务可外推到训练长度的 16 倍。
Read on arXiv PDF Hugging Face discussion
Topics & disciplines
More on LLMs
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.