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.

Related

• MemFly: On-the-Fly Memory Optimization via Information Bottleneck
• Acoustic-to-Text KV Compression for Full-Duplex Speech Models
• When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression
• ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents
• SALT: Salience-Aware Lexical Trie for Long-Context Compression

Source: arXiv cs.AI | 2026-09-28