相关论文: SuperLocalMemory V3: Information-Geometric Foundat…

Multimodal large language models (MLLMs) have exhibited remarkable performance in various visual tasks, yet still struggle with spatial reasoning. Recent efforts mitigate this by injecting geometric features from 3D foundation models, but…

Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting updates often cause collateral degradation on retaining…

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…

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…

Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: information persists indefinitely, retrieval…

The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies…

Being infinite dimensional, non-parametric information geometry has long faced an "intractability barrier" due to the fact that the Fisher-Rao metric is now a functional incurring difficulties in defining its inverse. This paper introduces…

AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural…

Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations,…

Retrieval-Augmented Generation (RAG) and vector-based search have become foundational tools for memory in AI systems, yet they struggle with abstraction, scalability, and semantic precision - especially in decentralized environments. We…

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory…

Large Language Model (LLM) agents exhibit remarkable conversational and reasoning capabilities but remain constrained by limited context windows and the lack of persistent memory. Recent efforts address these limitations via external memory…

Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing spatial video-language models improve geometric perception and long-range context…

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…

Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context boundaries or information overload within them. While human…

Visual information extraction (VIE) plays an important role in Document Intelligence. Generally, it is divided into two tasks: semantic entity recognition (SER) and relation extraction (RE). Recently, pre-trained models for documents have…

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,…

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…

Many learning-to-rank (LtR) algorithms focus on query-independent model, in which query and document do not lie in the same feature space, and the rankers rely on the feature ensemble about query-document pair instead of the similarity…

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…