Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory grow rapidly with prompt length. Flat token-stream processing and chunk-based retrieval can therefore spend substantial computation and context budget on text unrelated to the query. Offline-indexed RAG additionally introduces external storage and index management overhead, and typically appends retrieved evidence as raw text, increasing prefill cost and latency. H^{2}MT makes long-context inference structure-aware: it builds a semantic hierarchy offline, computes a memory embedding for each node via bottom-up post-order aggregation, and routes queries coarse-to-fine at inference to prune irrelevant branches early. On LongBench QA (NarrativeQA, HotpotQA, QASPER) and two structured technical-document settings, H MT achieves favorable quality efficiency trade-offs, delivering competitive ROUGE-L and F1 (where applicable) with lower peak GPU memory and time-to-first-token (TTFT) than prompt compression, memory-token methods, and retrieval-augmented generation baselines.
H$^{2}$MT: Semantic Hierarchy-Aware Hierarchical Memory Transformer
Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency and memory grow rapidly with prompt length.
- Preview

- Year
- 2026
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2605.24930ARXIV-DEFAULT
- TL;DR
- Semantic Scholar