Preprint
Aug 2026
PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory
Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: sequential chunk-wise updates can overwrite early critical evidence with later irrelevant content, and serial inter-chunk dependencies limit parallelism and cause latency t...
Da-Wei Liu, Haixu Song, Shuang Cheng et al.
· 0 citations