arXiv:2510.22752v2 Announce Type: replace-cross
Abstract: In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual inf...
By Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini, Yash Aggarwal, Zoran Tiganj
The paper introduces Temporal Semantic Memory (TSM), a framework that improves how large language model agents manage memory by addressing two key shortcomings: temporal inaccuracy and temporal fragmentation. TSM constructs a semantic timeline instead of a dialogue timeline, consolidating temporally continuous and semantically related information into durative memory. During retrieval, it aligns the query’s temporal intent with the semantic timeline, enabling the use of temporally appropriate durative memories and yielding up to a 12.2% accuracy boost over existing methods.
By Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
arXiv:2608. 02515v1 Announce Type: cross Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context.
By Zhichen Liu, Ruihan Sun, Hengjie Yang, Zipeng Wu, Zhaohan Chen, Xiaofan Zhang, Yang Xu
Long-term memory has become increasingly important for LLM agents that operate across extended interactions and evolving task contexts. Recent memory systems have made past experiences more persistent, compact, and retrievable, but retrieval alone does not ensure that a memory provides valid evidence for the current query.
arXiv:2606. 15405v1 Announce Type: cross Abstract: Long-term memory is essential for conversational agents to remain coherent across extended dialogues, follow through on commitments made many sessions earlier, and adapt their behaviour to each user.
By Weidong Guo, Dakai Wang, Zixuan Wang, Hui Liu, Yu Xu
A recurrent neural network with an episodic memory buffer was trained to infer situational context while watching naturalistic movies, using Bayesian inference to predict upcoming scenes. The inferred context modulates the network’s recurrent connectivity in a low‑rank manner, producing activity patterns that best match human fMRI responses. Context also guides episodic memory retrieval via a key‑value self‑attention system, enabling the model to retrieve memories faster and more accurately than a context‑agnostic version.
By Hayoung Song, JeongJun Park, Qihong Lu, Giacomo Vedovati, Monica D. Rosenberg, Zachariah M. Reagh, ShiNung Ching