Related papers: FSFM: A Biologically-Inspired Framework for Select…

Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these dimensions…

The incorporation of memory into agents is essential for numerous tasks within the domain of Reinforcement Learning (RL). In particular, memory is paramount for tasks that require the use of past information, adaptation to novel…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…

Personalized large language models (LLMs) rely on memory retrieval to incorporate user-specific histories, preferences, and contexts. Existing approaches either overload the LLM by feeding all the user's past memory into the prompt, which…

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential…

This study bridges cognitive science and neural network design by examining whether artificial models exhibit human-like forgetting curves. Drawing upon Ebbinghaus' seminal work on memory decay and principles of spaced repetition, we…

Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to…

Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent efficiency. However, existing studies treat the entire interaction trajectories equally,…

Recent advancements in Large Language Models (LLMs) have exhibited notable efficacy in question-answering (QA) tasks across diverse domains. Their prowess in integrating extensive web knowledge has fueled interest in developing LLM-based…

Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM…

Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier ones. Existing…

Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interactions. Existing memory systems mainly rely on static,…

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon…

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…

Large Language Model (LLM) agent systems have experienced rapid adoption across diverse domains, yet they suffer from critical user experience problems that limit their practical deployment. Through an empirical analysis of over 40,000…

Selective forgetting or removing information from deep neural networks (DNNs) is essential for continual learning and is challenging in controlling the DNNs. Such forgetting is crucial also in a practical sense since the deployed DNNs may…

Large Language Models (LLMs) are increasingly deployed in politically sensitive environments, where memorisation of personal data or confidential content raises regulatory concerns under frameworks such as the GDPR and its Right to be…

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

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…