Related papers: OCR-Memory: Optical Context Retrieval for Long-Hor…

Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion,…

LLM agents with persistent memory store information as flat factual records, providing little context for temporal reasoning, change tracking, or cross-session aggregation. Inspired by the drawing effect [3], we introduce dual-trace memory…

We propose an end-to-end recurrent encoder-decoder based sequence learning approach for printed text Optical Character Recognition (OCR). In contrast to present day existing state-of-art OCR solution which uses connectionist temporal…

In recent years, Multi-modal Large Language Models (MLLMs) have achieved strong performance in OCR-centric Visual Question Answering (VQA) tasks, illustrating their capability to process heterogeneous data and exhibit adaptability across…

Large Language Models (LLMs) have demonstrated impressive fluency and task competence in conversational settings. However, their effectiveness in multi-session and long-term interactions is hindered by limited memory persistence. Typical…

As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely…

Traditional online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout an agent's lifetime. However, a broad range of real-world applications are…

In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most research simply stores summarized versions of historical…

To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates…

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on…

Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often…

LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human experts, leading to…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

Academic documents are packed with texts, equations, tables, and figures, requiring comprehensive understanding for accurate Optical Character Recognition (OCR). While end-to-end OCR methods offer improved accuracy over layout-based…

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to…

Lifelong embodied navigation requires agents to accumulate, retain, and exploit spatial-semantic experience across tasks, enabling efficient exploration in novel environments and rapid goal reaching in familiar ones. While object-centric…

Large language models are increasingly deployed as research agents for deep search and long-horizon information seeking, yet their performance often degrades as interaction histories grow. This degradation, known as context rot, reflects a…

Overcoming the limited context limitations in early-generation LLMs, retrieval-augmented generation (RAG) has been a reliable solution for context-based answer generation in the past. Recently, the emergence of long-context LLMs allows the…

Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window…

Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across various visual reasoning tasks. However, their capabilities in text-rich image reasoning tasks remain understudied due to the absence of…