Related papers: Is Agent Memory a Database? Rethinking Data Founda…
Many real-world systems, such as transportation systems, ecological systems, and Internet systems, are complex systems. As an important tool for studying complex systems, computational experiments can map them into artificial society models…
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…
Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and…
Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and…
Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they…
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…
As Large Language Models (LLMs) evolve from text-completion tools into fully fledged agents operating in dynamic environments, they must address the challenge of continually learning and retaining long-term knowledge. Many biological…
We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…
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…
In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…
Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…
Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-horizon tasks and…
Memory-Augmented Generation (MAG) extends large language models with external memory to support long-context reasoning, but existing approaches universally treat memory as an external service that agents call into, delegating storage to…
Neuroscience data are highly fragmented across labs, formats, and experimental paradigms, and reuse often requires substantial manual effort. A persistent roadblock to data reuse and integration is the need to decipher bespoke and diverse…
Extraction at ingestion is the wrong primitive for agent memory: content discarded before the query is known cannot be recovered at retrieval time. We propose True Memory, a six-layer architecture that shifts the center of the system from a…
LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of…
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…
Long-horizon interactions between users and LLM-based assistants necessitate effective memory management, yet current approaches face challenges in training and evaluation of memory. Existing memory benchmarks rely on static, off-policy…
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal,…
We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generates questions from each agent's own trajectory, covering both…