The paper investigates how to inject knowledge into addressed memory modules of language models. Using controlled experiments on GPT‑2 and production‑memory tests on Qwen3.8‑Flash‑Next‑FP8 and DeepSeek‑V4.1‑Flash, the authors compare row‑only and row‑plus‑projection updates, with and without fixed module‑residual anchoring. Results show that while anchoring reduces drift, lexical hits do not guarantee entity‑specific retrieval, and first‑token rankings alone do not ensure full answer success, indicating that writable memory is feasible but limited in scope.
By Wei Gao (Shibei Qiyuan AI Technology), Cheng Tian (Shibei Qiyuan AI Technology), Duan Yang (Xi'an Jiaotong University), Jianqing Yin (Shibei Qiyuan AI Technology)
arXiv:2603. 06642v2 Announce Type: replace-cross Abstract: Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering catastrophic failure on exact-recall tasks.
By Swamynathan V P
arXiv:2606. 28876v2 Announce Type: replace-cross Abstract: We study memory-managed long-context attention: explicit bounded memory with a learned query-independent writer, lifecycle control, query-aware reading, calibrated sparse fallback, and frozen-LLM generation from raw evidence.
By Junyi Zou, Avrova Donz
arXiv:2606. 28876v1 Announce Type: cross Abstract: Long-context language models often conflate two different goals: compressing history into an efficient state, and maintaining reliable long-term memory.
By Junyi Zou, Avrova Donz
arXiv:2609.25853v1 Announce Type: new
Abstract: Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be...
By Mingyuan Li, Guangsheng Yu, Juyuan Zhang, Xu Wang, Zhibo Man, Haonan Zhang, Shaoxiong Ji
The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.
By Shweta Mishra, Shashank Mishra
arXiv:2607. 11020v1 Announce Type: cross Abstract: Continual learning promises a language model that keeps acquiring knowledge after training, with each new fact written into its weights.
By Charles O'Neill
arXiv:2607. 12204v1 Announce Type: new Abstract: Attention can be viewed as an online learner over context, yet existing test-time memories cannot certify that dropping a token leaves outputs unchanged or delete its influence outright.
By Vishwajith Ramesh
arXiv:2608. 12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions.
By Ganesh S
Delta N-gram introduces a forward‑only write path into a language model’s native hashed N‑gram table, preserving the pretrained table while adding evidence through a sparse patch Δ. The method uses a 4.1 M‑parameter writer that emits gated targets per event and applies a block‑averaged delta rule to keep each row a convex combination of its old value and the new targets. Experiments on a 0.6 B prototype and Qwen3.8‑Flash‑Next show that the delta writer maintains more document‑specific memory and reduces drift compared to online gradient writes, achieving stable performance over thousands of writes.
whyItMatters":"The approach allows continual updates to a language model’s memory without altering its pretrained parameters, enabling efficient, stable, and document‑specific knowledge retention during inference."
By Hao Wu
arXiv:2606.28876v4 Announce Type: replace-cross
Abstract: Memory-Mediated Learning Architecture (MMLA) separates slow base parameters theta, a bounded numerical policy carrier Phi, and a bounded auth...
By Junyi Zou, Avrova Donz
arXiv:2608.20873v3 Announce Type: replace
Abstract: A 4-bit quantized weight specifies a rounding cell rather than a single full-precision value. We introduce in-cell learning, a paradigm for writing...
By Zifeng Liu, Yaxin Lu, Xuanhan Wu, Zhiyong Du, Yiming Mao, Zhenhe Wang, Wenqi Shi, Zhengkun Jing, Linwei Liu