Related papers: Storage Is Not Memory: A Retrieval-Centered Archit…

LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context. While RAG-based approaches are increasingly adopted to overcome this limitation by storing interactions in external memory…

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…

Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agent identities, role, schemas, and dispatch structure but never sees an engine-level…

LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of…

Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from…

Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to…

This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is…

Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria such as relevance, salience, or summary quality. For an agent, however, memory is…

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…

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…

External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive…

A memory leak in an application deployed on the cloud can affect the availability and reliability of the application. Therefore, identifying and ultimately resolve it quickly is highly important. However, in the production environment…

Large Language Models (LLMs) are increasingly used as autonomous agents in complex, long-horizon applications, where effective memory is critical for sustained performance. Yet existing memory benchmarks are largely dialogue-centric, while…

MemPalace is an open-source AI memory system that applies the ancient method of loci (memory palace) spatial metaphor to organize long-term memory for large language models; launched in April 2026, it accumulated over 47,000 GitHub stars in…

Conversational agents struggle to handle long conversations due to context window limitations. Therefore, memory systems are developed to leverage essential historical information. Existing memory systems typically follow a pipeline of…

Memory mechanism is a core component of LLM-based agents, enabling reasoning and knowledge discovery over long-horizon contexts. Existing agent memory systems are typically designed within isolated paradigms (e.g., explicit, parametric, or…

Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. We study this question in a controlled cellular-automata (1dCA) framework that excludes memorisation by using…

We introduce \emph{Adaptive RAG Memory} (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a \emph{dynamic} memory substrate governed by selective remembrance and decay. Frequently retrieved…

A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes…

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…