English
Related papers

Related papers: MEMTRACK: Evaluating Long-Term Memory and State Tr…

200 papers

The rapid evolution of Multi-modal Large Language Models (MLLMs) has advanced workflow automation; however, existing research mainly targets performance upper bounds in static environments, overlooking robustness for stochastic real-world…

Artificial Intelligence · Computer Science 2026-01-14 Daocheng Fu , Jianbiao Mei , Rong Wu , Xuemeng Yang , Jia Xu , Ding Wang , Pinlong Cai , Yong Liu , Licheng Wen , Botian Shi

This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to improve the retention and retrieval of semantic information…

Computation and Language · Computer Science 2025-05-30 Yue Xing , Tao Yang , Yijiashun Qi , Minggu Wei , Yu Cheng , Honghui Xin

Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are worth storing in memory are different across users. This misalignment wastes limited memory…

Artificial Intelligence · Computer Science 2026-05-26 Yeonjun In , Wonjoong Kim , Sangwu Park , Kanghoon Yoon , Chanyoung Park

We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents,…

Computation and Language · Computer Science 2025-07-01 Prafulla Kumar Choubey , Xiangyu Peng , Shilpa Bhagavath , Kung-Hsiang Huang , Caiming Xiong , Chien-Sheng Wu

The Memory stress (Mess) framework provides a unified view of the memory system benchmarking, simulation and application profiling. The Mess benchmark provides a holistic and detailed memory system characterization. It is based on hundreds…

Despite the advancements and impressive performance of Multimodal Large Language Models (MLLMs) on benchmarks, their effectiveness in real-world, long-context, and multi-image tasks is unclear due to the benchmarks' limited scope. Existing…

Computation and Language · Computer Science 2024-05-16 Dingjie Song , Shunian Chen , Guiming Hardy Chen , Fei Yu , Xiang Wan , Benyou Wang

Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands. However, the progress is hampered by the lack of benchmarks with rigorous,…

Computation and Language · Computer Science 2026-02-16 Haiyun Guo , Zhiyan Hou , Yandu Sun , Jinghan He , Yu Chen , Yuzhe Zhou , Yuheng Jia , Jinqiao Wang , Tat-Seng Chua

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

Current AI agents excel in familiar settings, but fail sharply when faced with novel tasks with unseen vocabularies -- a core limitation of procedural memory systems. We present the first benchmark that isolates procedural memory retrieval…

Computation and Language · Computer Science 2025-12-01 Ishant Kohar , Aswanth Krishnan

As large language models (LLMs) advance across diverse tasks, the need for comprehensive evaluation beyond single metrics becomes increasingly important. To fully assess LLM intelligence, it is crucial to examine their interactive dynamics…

Computation and Language · Computer Science 2025-09-23 Junhao Chen , Jingbo Sun , Xiang Li , Haidong Xin , Yuhao Xue , Yibin Xu , Hao Zhao

We present a benchmark targeting a novel class of systems: semantic query processing engines. Those systems rely inherently on generative and reasoning capabilities of state-of-the-art large language models (LLMs). They extend SQL with…

Large language model assistants are increasingly expected to retain and reason over information accumulated across many sessions. We introduce EngramaBench, a benchmark for long-term conversational memory built around five personas, one…

Computation and Language · Computer Science 2026-04-24 Julian Acuna

Industrial automation increasingly requires flexible control strategies that can adapt to changing tasks and environments. Agents based on Large Language Models (LLMs) offer potential for such adaptive planning and execution but lack…

Artificial Intelligence · Computer Science 2025-12-04 Niklas Jobs , Luis Miguel Vieira da Silva , Jayanth Somashekaraiah , Maximilian Weigand , David Kube , Felix Gehlhoff

Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…

Computation and Language · Computer Science 2026-03-10 Muxin Fu , Xiangyuan Xue , Yafu Li , Zefeng He , Siyuan Huang , Xiaoye Qu , Yu Cheng , Yang Yang

The integration of large language model (LLM) agents into telecom networks introduces new challenges, related to intent recognition, tool execution, and resolution generation, while taking into consideration different operational…

Computation and Language · Computer Science 2026-04-09 Lina Bariah , Brahim Mefgouda , Farbod Tavakkoli , Enrique Molero , Louis Powell , Merouane Debbah

Static performance estimation is essential during compile-time analysis, yet traditional runtime-based methods are costly and platform-dependent. We investigate mems, the number of memory accesses, as a static and architecture-independent…

Software Engineering · Computer Science 2025-05-13 Liwei Zhang , Baoquan Cui , Xutong Ma , Jian Zhang

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar…

Artificial Intelligence · Computer Science 2026-03-12 Gaodan Fang , Vatche Isahagian , K. R. Jayaram , Ritesh Kumar , Vinod Muthusamy , Punleuk Oum , Gegi Thomas

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative…

Artificial Intelligence · Computer Science 2025-04-17 Peijie Yu , Yifan Yang , Jinjian Li , Zelong Zhang , Haorui Wang , Xiao Feng , Feng Zhang

Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant…

Artificial Intelligence · Computer Science 2026-04-10 Ruoran Li , Xinghua Zhang , Haiyang Yu , Shitong Duan , Xiang Li , Wenxin Xiang , Chonghua Liao , Xudong Guo , Yongbin Li , Jinli Suo