Related papers: MemReader: From Passive to Active Extraction for L…

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…

Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this experience learning capability enhances agentic autonomy, it…

Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to inefficient memory management. Existing approaches face a fundamental trade-off between efficiency…

Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a…

Standard Retrieval Augmented Generation (RAG) is poorly matched to agent memory. Unlike large heterogeneous corpora, agent memory forms a bounded and coherent interaction stream in which many spans are highly correlated or near duplicates.…

We introduce LEGOMem, a modular procedural memory framework for multi-agent large language model (LLM) systems in workflow automation. LEGOMem decomposes past task trajectories into reusable memory units and flexibly allocates them across…

Recently, recurrent large language models (Recurrent LLMs) with linear computational complexity have re-emerged as efficient alternatives to self-attention-based LLMs (Self-Attention LLMs), which have quadratic complexity. However,…

Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments. To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism…

Extraction at ingestion is the wrong primitive for agent memory: content discarded before the query is known cannot be recovered at retrieval time. We propose True Memory, a six-layer architecture that shifts the center of the system from a…

Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…

Long story generation remains a challenge for existing large language models (LLMs), primarily due to two main factors: (1) discourse coherence, which requires plot consistency, logical coherence, and completeness in the long-form…

Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems that extract, retrieve, and apply information across long-running conversations. However,…

Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative…

Multi-agent large language model (LLM) systems have shown strong potential in complex reasoning and collaborative decision-making tasks. However, most existing coordination schemes rely on static or full-context routing strategies, which…

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…

The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…

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…

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…

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…

Humans routinely rely on memory to perform tasks, yet most robot policies lack this capability; our goal is to endow robot policies with the same ability. Naively conditioning on long observation histories is computationally expensive and…