Related papers: Governing Evolving Memory in LLM Agents: Risks, Me…

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…

Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augment reasoning. As researchers create more complex memory architectures, it becomes increasingly…

Agent memory shapes how Large Language Model (LLM)-powered agents, akin to the human brain, progressively refine themselves through environment interactions. Existing paradigms remain constrained: parametric memory forcibly adjusts model…

Constructivist epistemology argues that knowledge is actively constructed rather than passively copied. Despite the generative nature of Large Language Models (LLMs), most existing agent memory systems are still based on dense retrieval.…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attention, the field has also become increasingly fragmented.…

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…

As Large Language Models (LLMs) continue to be increasingly applied across various domains, their widespread adoption necessitates rigorous monitoring to prevent unintended negative consequences and ensure robustness. Furthermore, LLMs must…

State space models (SSMs) have emerged as a powerful framework for modelling long-range dependencies in sequence data. Unlike traditional recurrent neural networks (RNNs) and convolutional neural networks (CNNs), SSMs offer a structured and…

Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…

Large language models (LLMs) deployed in user-facing applications require long-horizon consistency: the ability to remember prior interactions, respect user preferences, and ground reasoning in past events. However, contemporary memory…

As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an ``all-or-nothing'' approach to…

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack…

Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these…

Long-term conversational agents require effective memory management to handle dialogue histories that exceed the context window of large language models (LLMs). Existing methods based on fact extraction or summarization reduce redundancy…

Large language models (LLMs) have emerged as effective action policies for sequential decision-making (SDM) tasks due to their extensive prior knowledge. However, this broad yet general knowledge is often insufficient for specific…

Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: information persists indefinitely, retrieval…

LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety depend not only on individual model outputs, but also on what…

Large language models often suffer from fact loss, timeline confusion, persona drift, and reduced stability during long-range interaction, especially under high-noise knowledge bases, context clearing, and cross-model transfer. To address…

Large language model (LLM)-based agents have recently gained considerable attention due to the powerful reasoning capabilities of LLMs. Existing research predominantly focuses on enhancing the task performance of these agents in diverse…