Related papers: SuperLocalMemory V3.3: The Living Brain -- Biologi…

Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…

Large Language Model (LLM)-based agents are increasingly employed to automate complex software engineering tasks, such as program repair and issue resolution. These agents operate by autonomously generating natural language thoughts,…

Reasoning models enhance problem-solving by scaling test-time compute, yet they face a critical paradox: excessive thinking tokens often degrade performance rather than improve it. We attribute this to a fundamental architectural flaw:…

LLM/VLM-based digital agents have advanced rapidly thanks to scalable sandboxes for coding, web navigation, and computer use, which provide rich interactive training grounds. In contrast, embodied agents still lack abundant, diverse, and…

Current Vision-Language Models (VLMs) fail at quantitative spatial reasoning because their architectures destroy pixel-level information required for counting and measurements. Vision encoders compress images through patch embeddings,…

Large Language Model (LLM) agent systems have experienced rapid adoption across diverse domains, yet they suffer from critical user experience problems that limit their practical deployment. Through an empirical analysis of over 40,000…

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low…

Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments without prior maps or task-specific training which remains a significant challenge. Although recent advancements in vision-language…

Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization,…

Recent advancements in large language models (LLMs) have greatly improved their capabilities on complex reasoning tasks through Long Chain-of-Thought (CoT). However, this approach often results in substantial redundancy, impairing…

Large multimodal models exhibit remarkable intelligence, yet their embodied cognitive abilities during motion in open-ended urban 3D space remain to be explored. We introduce a benchmark to evaluate whether video-large language models…

Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and…

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…

We present a memory system for AI agents that treats stored information as continuous fields governed by partial differential equations rather than discrete entries in a database. The approach draws from classical field theory: memories…

Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LLMs are not suitable for frequent retraining. However,…

Humans and animals have the ability to continuously learn new information over their lifetime without losing previously acquired knowledge. However, artificial neural networks struggle with this due to new information conflicting with old…

Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adaptation (LoRA) is widely used for such memory updates, existing studies mainly rely on…

The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics. This study investigates the internal neural representations of cognitive complexity using Bloom's…

We present SpatialMem, a memory-centric system for long-horizon, language-grounded retrieval and QA from egocentric video, where metric 3D serves as an interpretable indexing scaffold rather than an explicit mapping objective. Starting from…