Related papers: MemX: A Local-First Long-Term Memory System for AI…

Long-term memory is essential for natural, realistic dialogue. However, current large language model (LLM) memory systems rely on either brute-force context expansion or static retrieval pipelines that fail on edge-constrained devices. We…

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,…

Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing deep search agents for memory system repeat past error…

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

Reservoir computing (RC) offers a neuromorphic framework that is particularly effective for processing spatiotemporal signals. Known for its temporal processing prowess, RC significantly lowers training costs compared to conventional…

Large language models (LLMs) operate within fixed context windows that fundamentally limit conversational continuity. When context fills, compaction discards history irreversibly; when sessions end, all memory resets to zero. Existing…

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 systems have been designed to leverage past experiences in Large Language Model (LLM) agents. However, many deployed memory systems primarily optimize compression and storage, with comparatively less emphasis on explicit, closed-loop…

In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage paradigm, but generic reranking models rely on semantic…

Consistent hashing is used in distributed systems and networking applications to spread data evenly and efficiently across a cluster of nodes. In this paper, we present MementoHash, a novel consistent hashing algorithm that eliminates known…

Retrieving relevant past interactions from long-term conversational memory typically relies on large dense retrieval models (110M-1.5B parameters) or LLM-augmented indexing. We introduce SelRoute, a framework that routes each query to a…

Existing works increasingly adopt memory-centric mechanisms to process long contexts in a segment manner, and effective memory management is one of the key capabilities that enables large language models to effectively propagate information…

Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains, yet the limitation of context window poses challenges for the model on long-range inference tasks and necessitates a memory…

With the growing demand for intelligent in-vehicle experiences, vehicle-based agents are evolving from simple assistants to long-term companions. This evolution requires agents to continuously model multi-user preferences and make reliable…

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online…

Recent conversational memory systems invest heavily in LLM-based structuring at ingestion time and learned retrieval policies at query time. We show that neither is necessary. SmartSearch retrieves from raw, unstructured conversation…

Large vision-language models have recently demonstrated impressive performance in planning and control tasks, driving interest in their application to real-world robotics. However, deploying these models for reasoning in embodied contexts…

Recent works have highlighted the significance of memory mechanisms in LLM-based agents, which enable them to store observed information and adapt to dynamic environments. However, evaluating their memory capabilities still remains…

AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space…

The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone…