Related papers: Memora: A Harmonic Memory Representation Balancing…

Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with…

Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong performance in…

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…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM…

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term…

A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the…

Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require maintaining task state across many interface transitions. Existing agents typically rely…

The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge internalization and reasoning capabilities. To address this…

Retrieval-augmented generation (RAG) enables large language models (LLMs) to dynamically access external information, which is powerful for answering questions over previously unseen documents. Nonetheless, they struggle with high-level…

Accurate recall from large scale memories remains a core challenge for memory augmented AI assistants performing question answering (QA), especially in similarity dense scenarios where existing methods mainly rely on semantic distance to…

Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the…

The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating…

Retrieval Augmented Generation (RAG) is a promising technique for mitigating two key limitations of large language models (LLMs): outdated information and hallucinations. RAG system stores documents as embedding vectors in a database. Given…

LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these…

Humans learn compositional and causal abstraction, \ie, knowledge, in response to the structure of naturalistic tasks. When presented with a problem-solving task involving some objects, toddlers would first interact with these objects to…

Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and…

Domain-specific QA systems require not just generative fluency but high factual accuracy grounded in structured expert knowledge. While recent Retrieval-Augmented Generation (RAG) frameworks improve context recall, they struggle with…

Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory…

Large language model agents heavily rely on external memory to support knowledge reuse and complex reasoning tasks. Yet most memory systems store experiences in a single global retrieval pool which can gradually dilute or corrupt stored…