Related papers: DeltaMem: Towards Agentic Memory Management via Re…
Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…
Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet most existing systems treat construction, retrieval, and utilization as isolated subroutines. This creates two coupled challenges: strategic…
LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We…
Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In…
Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as…
Autonomous driving has made significant strides through data-driven techniques, achieving robust performance in standardized tasks. However, existing methods frequently overlook user-specific preferences, offering limited scope for…
Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large language model (LLM)-based methods have achieved promising results, most of them still rely on a…
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…
Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…
Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill…
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…
MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However,…
Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable processing, their passive memory update strategy often fails…
Autonomy via agents using large language models (LLMs) for personalized, standardized tasks boosts human efficiency. Automating web tasks (like booking hotels within a budget) is increasingly sought after. Fulfilling practical needs, the…
User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has evolved from latent embeddings to semantic memory. While existing memory mechanisms…
An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but…
Memory systems are critical for LLMs, mitigating context window limitations and supporting long-horizon user-LLM interactions. Such systems typically comprise multiple agents responsible for memory construction and retrieval. Existing…
In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI. Our approach decomposes the agent into two specialized components: (1) a large language…
Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…
The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…