Related papers: Memory-Induced Tool-Drift in LLM Agents

Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…

Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized agents prioritizes utility and user experience, treating memory as a neutral component and…

Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate this phenomenon, we…

Autonomous AI agents increasingly extend their capabilities through Agent Skills: modular filesystem packages whose SKILL.md files describe when and how agents should use them. While this design enables scalable, on-demand capability…

LLMs are increasingly embedded in everyday decision-making, yet their outputs can encode subtle, unintended behaviours that shape user beliefs and actions. We refer to these covert, goal-directed behaviours as hidden intentions, which may…

LLM-based agents have been widely applied as personal assistants, capable of memorizing information from user messages and responding to personal queries. However, there still lacks an objective and automatic evaluation on their memory…

Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that require specialized processing or up-to-date data. While…

Large language model unlearning has become a critical challenge in ensuring safety and controlled model behavior by removing undesired data-model influences from the pretrained model while preserving general utility. Significant recent…

Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the multifaceted nature of complex memory systems, such as dynamic state tracking and…

Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments.…

AI agents are increasingly used in long, multi-turn workflows in both research and enterprise settings. As interactions grow, agent behavior often degrades due to loss of constraint focus, error accumulation, and memory-induced drift. This…

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…

Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal clinical scales remains poorly understood. We benchmark three frontier LLM families…

The increasing deployment of advanced digital technologies such as Internet of Things (IoT) devices and Cyber-Physical Systems (CPS) in industrial environments is enabling the productive use of machine learning (ML) algorithms in the…

While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks. Monitoring step-level tool invocation behaviors in real time and proactively intervening before…

Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for…

When an LLM-based embodied agent fails at a household task, the culprit could be misidentified objects, forgotten sub-goals, or poor action sequencing -- yet existing benchmarks report only a single success rate, making it impossible to…

Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases. While persistent…

Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform…

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods are…