
ZH
Zihong He, Junxiao Shen, Chen Liang, Hai-Ning Liang
· 1 min read
ResearcharXiv cs.AI
HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents
arXiv:2609.30797v1 Announce Type: new
Abstract: Text-based memory and context compression support reuse of past interactions. Resizing continuous memory changes the input to a frozen LLM, coupling capacity allocation with readout. We propose Hard-Origin Adaptively Softened Memory (HasMem). Frozen hard-prompt embeddings provide a verifiable initial state. A controller adjusts memory widths, a Writer re-encodes resized entries, and Reader and Global provide readout adaptation and cross-turn state. On all $535$ questions in a reconstruction probe derived from the Multi-Session Chat (MSC) development split, the main configuration achieves lexical F1 of $95.3$ ($+4.4$ percentage points) at $93.6\%$ of the hard reference's framed memory positions. With approximately matched per-question target body budgets, six configurations at mean per-entry retention around $0.83$--$0.91$ exceed rule-based re-encoding by $8.0$--$23.6$ exact-match (EM) percentage points. With fixed model parameters and rule target width ratio $0.75$, Global's EM gain passes a user-level exact paired test with Bonferroni correction over eight comparisons. On all $500$ LongMemEval-S questions, local lexical F1 rises from the hard reference's $3.4$ to $8.9$, and answer negative log-likelihood (NLL) falls from $12.257$ to $5.274$. F1 gains accompany lower EM on both evaluations.
Original source
This story was published by arXiv cs.AI and written by Zihong He, Junxiao Shen, Chen Liang, Hai-Ning Liang. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


