English
Related papers

Related papers: Remember the Decision, Not the Description: A Rate…

200 papers

Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative…

Computation and Language · Computer Science 2026-03-17 Yuri Kuratov , Matvey Kairov , Aydar Bulatov , Ivan Rodkin , Mikhail Burtsev

Recent works have highlighted the significance of memory mechanisms in LLM-based agents, which enable them to store observed information and adapt to dynamic environments. However, evaluating their memory capabilities still remains…

Computation and Language · Computer Science 2025-06-30 Haoran Tan , Zeyu Zhang , Chen Ma , Xu Chen , Quanyu Dai , Zhenhua Dong

Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy memory, multi-step reasoning, and binding regulatory constraints. Current evaluation…

Artificial Intelligence · Computer Science 2026-04-22 Vasundra Srininvasan

Large vision-language models have recently demonstrated impressive performance in planning and control tasks, driving interest in their application to real-world robotics. However, deploying these models for reasoning in embodied contexts…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Karmesh Yadav , Yusuf Ali , Gunshi Gupta , Yarin Gal , Zsolt Kira

World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context window often leads to failures in maintaining long-term…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Zeqi Xiao , Yushi Lan , Yifan Zhou , Wenqi Ouyang , Shuai Yang , Yanhong Zeng , Xingang Pan

Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail to properly model the temporal dimension of memory in two…

Artificial Intelligence · Computer Science 2026-01-13 Miao Su , Yucan Guo , Zhongni Hou , Long Bai , Zixuan Li , Yufei Zhang , Guojun Yin , Wei Lin , Xiaolong Jin , Jiafeng Guo , Xueqi Cheng

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…

Computation and Language · Computer Science 2025-04-01 Yihuai Hong , Dian Zhou , Meng Cao , Lei Yu , Zhijing Jin

Enterprise deployment of long-horizon decision agents in regulated domains (underwriting, claims adjudication, tax examination) is dominated by retrieval-augmented pipelines despite a decade of increasingly sophisticated stateful memory…

Artificial Intelligence · Computer Science 2026-04-23 Vasundra Srinivasan

Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries,…

Robotics · Computer Science 2026-03-03 Ji Li , Bo Wang , Jing Xia , Mingyi Li , Shiyan Hu

Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new…

Computation and Language · Computer Science 2026-05-08 Hanxiang Chao , Yihan Bai , Rui Sheng , Tianle Li , Yushi Sun

Large Language Models (LLMs) represent a landmark achievement in Artificial Intelligence (AI), demonstrating unprecedented proficiency in procedural tasks such as text generation, code completion, and conversational coherence. These…

Artificial Intelligence · Computer Science 2025-05-07 Schaun Wheeler , Olivier Jeunen

LLM agents increasingly rely on memory mechanisms to reuse knowledge from past problem-solving experiences. However, existing methods typically construct memory for a single agent and reuse it with the same underlying model, tightly…

Artificial Intelligence · Computer Science 2026-05-29 Yurui Chang , Yiran Wu , Qingyun Wu , Lu Lin

Memory-Augmented Generation (MAG) extends large language models with external memory to support long-context reasoning, but existing approaches universally treat memory as an external service that agents call into, delegating storage to…

Artificial Intelligence · Computer Science 2026-04-03 Andy Nguyen , Danh Doan , Hoang Pham , Bao Ha , Dat Pham , Linh Nguyen , Hieu Nguyen , Thien Nguyen , Cuong Do , Phat Nguyen , Toan Nguyen

Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Wenbo Hu , Yining Hong , Yanjun Wang , Leison Gao , Zibu Wei , Xingcheng Yao , Nanyun Peng , Yonatan Bitton , Idan Szpektor , Kai-Wei Chang

Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates…

Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)-based agents, where extraction (distilling insights from experience) and management (updating the memory bank) must be tightly coordinated. Existing…

Computation and Language · Computer Science 2026-02-12 Yongshi Ye , Hui Jiang , Feihu Jiang , Tian Lan , Yichao Du , Biao Fu , Xiaodong Shi , Qianghuai Jia , Longyue Wang , Weihua Luo

In today's assistant landscape, personalisation enhances interactions, fosters long-term relationships, and deepens engagement. However, many systems struggle with retaining user preferences, leading to repetitive user requests and…

Artificial Intelligence · Computer Science 2025-01-17 Johannes Kirmayr , Lukas Stappen , Phillip Schneider , Florian Matthes , Elisabeth André

Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversations or text but fails to capture how memory is used to…

Computation and Language · Computer Science 2026-02-19 Zexue He , Yu Wang , Churan Zhi , Yuanzhe Hu , Tzu-Ping Chen , Lang Yin , Ze Chen , Tong Arthur Wu , Siru Ouyang , Zihan Wang , Jiaxin Pei , Julian McAuley , Yejin Choi , Alex Pentland

Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these dimensions…

Multiagent Systems · Computer Science 2026-04-07 Shanglin Wu , Yuyang Luo , Yueqing Liang , Kaiwen Shi , Yanfang Ye , Ali Payani , Kai Shu

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete…

Machine Learning · Computer Science 2026-03-11 Lina Berrayana , Ahmed Heakl , Abdullah Sohail , Thomas Hofmann , Salman Khan , Wei Chen