Related papers: Remember Your Trace: Memory-Guided Long-Horizon Ag…

To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment. In the current paradigm of training transformer-based…

Layout design is a crucial step in developing mobile app pages. However, crafting satisfactory designs is time-intensive for designers: they need to consider which controls and content to present on the page, and then repeatedly adjust…

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact…

LLM-based multimodal emotion recognition relies on static parametric memory and often hallucinates when interpreting nuanced affective states. In this paper, given that single-round retrieval-augmented generation is highly susceptible to…

Long-video understanding remains a significant challenge for Multimodal Large Language Models (MLLMs) due to inherent token limitations and the complexity of capturing long-term temporal dependencies. Existing methods often fail to capture…

In this paper we introduce ResearchCodeAgent, a novel multi-agent system leveraging large language models (LLMs) agents to automate the codification of research methodologies described in machine learning literature. The system bridges the…

Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code…

Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversations or text but fails to capture how memory is used to…

Large language models based Multi Agent Systems (MAS) have demonstrated promising performance for enhancing the efficiency and accuracy of code generation tasks. However,most existing methods follow a conventional sequence of planning,…

Traditional enterprises face significant challenges in processing business documents, where tasks like extracting transport references from invoices remain largely manual despite their crucial role in logistics operations. While Large…

Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts.…

Recovering accurate architecture from large-scale legacy software is hindered by architectural drift, missing relations, and the limited context of Large Language Models (LLMs). We present ArchAgent, a scalable agent-based framework that…

The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous,…

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…

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven…

Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the…

With the rapid advancement of large language models (LLMs), Multi-agent Systems (MAS) have achieved significant progress in various application scenarios. However, substantial challenges remain in designing versatile, robust, and efficient…

Heterogeneous Multi-Embodied Agent Systems involve coordinating multiple embodied agents with diverse capabilities to accomplish tasks in dynamic environments. This process requires the collection, generation, and consumption of massive,…

Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based…

Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing…