The paper investigates Associative Recall (AR) in the Mamba architecture, showing that Mamba implicitly learns linear hash functions to perform recall. It identifies the low‑level circuit responsible for this behavior and develops a theoretical framework—Recall Scaling Laws—based on similarity‑preserving hashing principles. The framework predicts embedding and state dimensions for perfect recall, recall success probability, and analyzes multi‑layer and multi‑head SSM patterns, with empirical results confirming its accuracy.
By Yuval Koren, Assaf Ben-Kish, Raja Giryes, Lior Wolf, Itamar Zimerman
arXiv:2605. 05066v2 Announce Type: replace-cross Abstract: We identify and prove a fundamental trade-off governing long-sequence models: no model can simultaneously achieve (i) per-step computation independent of sequence length (Efficiency), (ii) state size independent of sequence length (Compactness), and (iii) the ability to recall a number of historical facts proportional to sequence length (Recall).
By Yan Zhou
arXiv:2609.25802v1 Announce Type: new
Abstract: We introduce latest exact match attention (LEMA), an attention variant for transformers where queries and keys are binarized and each query attends onl...
By Moritz Br\"osamle
arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.
By Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu, Levina Li, Dong Liu, Xiao Liang, Rui Sun, Yubei Li, Edward Sun, Haozheng Luo, Zhaolu Kang, Aylin Caliskan, Kai-Wei Chang, Ying Nian Wu
arXiv:2602. 03315v2 Announce Type: replace Abstract: Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks.
By Menglin Xia, Xuchao Zhang, Shantanu Dixit, Paramaguru Harimurugan, Rujia Wang, Victor Ruhle, Robert Sim, Chetan Bansal, Saravan Rajmohan
arXiv:2601.12075v2 Announce Type: replace
Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information...
By Mehrdad Farahani, Franziska Penzkofer, Richard Johansson
arXiv:2607. 20458v1 Announce Type: cross Abstract: Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain everything indiscriminately or apply uniform forgetting heuristics that fail to distinguish relevant from irrelevant knowledge.
By Haowen Lai
Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured memories to reflective insight stores, access memory through fixed, hand-designed heuristics.
arXiv:2607. 09889v1 Announce Type: cross Abstract: Fixed-state sequence models compress an unbounded past into a bounded state, which caps their associative recall at roughly the state dimension; attention escapes the cap by keeping a key-value entry for every token, at quadratic compute and a cache that grows with the sequence.
By Siddharth Pal, Viktoria Rojkova
arXiv:2602. 09075v3 Announce Type: replace-cross Abstract: In-Context Learning (ICL) in transformers acts as an online associative memory and is believed to underpin their high performance on complex sequence processing tasks.
By Djohan Bonnet, Jamie Lohoff, Jan Finkbeiner, Elidona Skhikerujah, Emre Neftci
arXiv:2607. 22562v1 Announce Type: new Abstract: Managing long-context dependencies remains a primary bottleneck in LLM agents, as redundant and irrelevant information can degrade multi-step reasoning.
By Ning Yang, Siqi Li, Miaoxin Shen, Yuan Zhou, Meng Zhang, Tong Li, Haijun Zhang
arXiv:2602. 07885v2 Announce Type: replace Abstract: Long-term memory enables large language model agents to tackle complex tasks through historical interactions.
By Zhenyuan Zhang, Xianzhang Jia, Zhiqin Yang, Zhenbo Song, Wei Xue, Sirui Han, Yike Guo