Related papers: Collaborative Memory: Multi-User Memory Sharing in…

Learning in high dimensional continuous tasks is challenging, mainly when the experience replay memory is very limited. We introduce a simple yet effective experience sharing mechanism for deterministic policies in continuous action domains…

While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also…

Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic…

In continual learning (CL), an AI agent (e.g., autonomous vehicles or robotics) learns from non-stationary data streams under dynamic environments. For the practical deployment of such applications, it is important to guarantee robustness…

LLM-based agents have made significant advancements in interactive environments, such as mobile operations and web browsing, and other domains beyond computer using. Current multi-agent systems universally excel in performance, compared to…

We introduce LEGOMem, a modular procedural memory framework for multi-agent large language model (LLM) systems in workflow automation. LEGOMem decomposes past task trajectories into reusable memory units and flexibly allocates them across…

Recent advancements in the field of AI agents have impacted the way we work, enabling greater automation and collaboration between humans and agents. In the data visualization field, multi-agent systems can be useful for employing agents…

LLM agents operating under organizational policies must comply with authorization constraints typically specified in natural language. In practice, such specifications inevitably contain ambiguities and logical or semantic gaps that cause…

Large language models (LLMs) have revolutionized AI, but are constrained by limited context windows, hindering their utility in tasks like extended conversations and document analysis. To enable using context beyond limited context windows,…

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…

Large Language Model (LLM) agents have shown significant autonomous capabilities in dynamically searching and incorporating relevant tools or Model Context Protocol (MCP) servers for individual queries. However, fixed context windows limit…

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments…

We propose a new framework for multi-agent reinforcement learning (MARL), where the agents cooperate in a time-evolving network with latent community structures and mixed memberships. Unlike traditional neighbor-based or fixed interaction…

With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent…

Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term, cross-session user states. Existing approaches, including…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…

In the field of MLLM-based GUI agents, compared to smartphones, the PC scenario not only features a more complex interactive environment, but also involves more intricate intra- and inter-app workflows. To address these issues, we propose a…

Multi-agent systems (MASs) can autonomously learn to solve previously unknown tasks by means of each agent's individual intelligence as well as by collaborating and exploiting collective intelligence. This article considers a group of…

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…

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…