Related papers: Structured Episodic Event Memory
Retrieval-Augmented Generation (RAG) is widely employed to mitigate risks such as hallucinations and knowledge obsolescence in medical question answering, yet its predominantly single-round, static retrieval paradigm misaligns with the…
Robots and autonomous systems require an understanding of complex events (CEs) from sensor data to interact with their environments and humans effectively. Traditional end-to-end neural architectures, despite processing sensor data…
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM)…
LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…
Structured representations, exemplified by Abstract Meaning Representation (AMR), have long been pivotal in computational linguistics. However, their role remains ambiguous in the Large Language Models (LLMs) era. Initial attempts to…
Semiparametric language models (LMs) have shown promise in continuously learning from new text data by combining a parameterized neural LM with a growable non-parametric memory for memorizing new content. However, conventional…
Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However,…
Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…
Owing to recent advancements, Large Language Models (LLMs) can now be deployed as agents for increasingly complex decision-making applications in areas including robotics, gaming, and API integration. However, reflecting past experiences in…
Prior work has shown that coupling sequential latent variable models with semantic ontological knowledge can improve the representational capabilities of event modeling approaches. In this work, we present a novel, doubly hierarchical,…
We propose \textbf{FLAMES (Fast Long-range Adaptive Memory for Event-based Systems)}, a novel hybrid framework integrating structured state-space dynamics with event-driven computation. At its core, the \textit{Spike-Aware HiPPO (SA-HiPPO)…
Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing…
Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and…
Episodic memory-based methods can rapidly latch onto past successful strategies by a non-parametric memory and improve sample efficiency of traditional reinforcement learning. However, little effort is put into the continuous domain, where…
Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their underexposure during pre-training and rigid text-to-structure…
The performance bottleneck of Automatic Speech Recognition (ASR) in stuttering speech scenarios has limited its applicability in domains such as speech rehabilitation. This paper proposed an LLM-driven ASR-SED multi-task learning framework…
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…
Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user…
Autonomous LLM agents require structured long-term memory, yet current "append-and-evolve" systems like A-MEM face O(N^2) write-latency and excessive token costs. We introduce D-MEM (Dopamine-Gated Agentic Memory), a biologically inspired…
Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…