Related papers: Been There, Done That: Meta-Learning with Episodic…

We envision a continuous collaborative learning system where groups of LLM agents work together to solve reasoning problems, drawing on memory they collectively build to improve performance as they gain experience. This work establishes the…

Biological neural networks are capable of recruiting different sets of neurons to encode different memories. However, when training artificial neural networks on a set of tasks, typically, no mechanism is employed for selectively producing…

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar…

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…

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization…

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,…

Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models…

Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input…

A lifelong learning agent is able to continually learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents that adapt in this way is that neural systems struggle to retain…

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too…

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…

Continual Learning in artificial neural networks suffers from interference and forgetting when different tasks are learned sequentially. This paper introduces the Active Long Term Memory Networks (A-LTM), a model of sequential multi-task…

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains, yet the limitation of context window poses challenges for the model on long-range inference tasks and necessitates a memory…

Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting…

Navigating complex environments requires robots to effectively store observations as memories and leverage them to answer human queries about spatial locations, which is a critical yet underexplored research challenge. While prior work has…

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to…

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…

Recent advancements in large language models (LLMs) have brought significant changes to various domains, especially through LLM-driven autonomous agents. A representative scenario is in software development, where LLM agents demonstrate…