Related papers: Hierarchical Memory for High-Efficiency Long-Term …

As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely…

External memory is a key component of modern large language model (LLM) systems, enabling long-term interaction and personalization. Despite its importance, memory management is still largely driven by hand-designed heuristics, offering…

Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static predictors to interactive systems capable of…

Large language models (LLMs) have achieved impressive linguistic capabilities. However, a key limitation persists in their lack of human-like memory faculties. LLMs exhibit constrained memory retention across sequential interactions,…

Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmarks for agents mostly…

Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform…

Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM)…

While Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge, conventional single-agent RAG remains fundamentally limited in resolving complex queries demanding coordinated reasoning across…

Recent advancements in LLM-powered agents have demonstrated significant potential in generating human-like responses; however, they continue to face challenges in maintaining long-term interactions within complex environments, primarily due…

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

Driven by the development of persistent, self-adapting autonomous agents, equipping these systems with high-fidelity memory access for long-horizon reasoning has emerged as a critical requirement. However, prevalent retrieval-based memory…

In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most research simply stores summarized versions of historical…

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.…

Agent memory has been touted as a dimension of growth for LLM-based applications, enabling agents that can accumulate experience, adapt across sessions, and move beyond single-shot question answering. The current generation of agent memory…

Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing…

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…

Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift,…