Related papers: Visual Inception: Compromising Long-term Planning …

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…

Collective Perception has attracted significant attention in recent years due to its advantage for mitigating occlusion and expanding the field-of-view, thereby enhancing reliability, efficiency, and, most crucially, decision-making safety.…

Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augmented LLM agents rely on "always-on" retrieval and "flat"…

Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection, especially through visual inputs. We introduce AgentTypo, a black-box…

The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet,…

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as…

Humans navigate unfamiliar environments using episodic simulation and episodic memory, which facilitate a deeper understanding of the complex relationships between environments and objects. Developing an imaginative memory system inspired…

Eliciting reasoning has emerged as a powerful technique for improving the performance of large language models (LLMs) on complex tasks by inducing thinking. However, their effectiveness in realistic user-engaged agent scenarios remains…

Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reasoning over multiple pieces of information. However, existing…

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…

Owing to powerful natural language processing and generative capabilities, large language model (LLM) agents have emerged as a promising solution for enhancing recommendation systems via user simulation. However, in the realm of video…

Large Language Model (LLM)-based agentic systems have shown growing promise in tackling complex, multi-step tasks through autonomous planning, reasoning, and interaction with external environments. However, the stochastic nature of LLM…

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…

Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…

Real-world image restoration (IR) is inherently complex and often requires combining multiple specialized models to address diverse degradations. Inspired by human problem-solving, we propose AgenticIR, an agentic system that mimics the…

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger…

Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write…

Current Large Language Models (LLMs) are confronted with overwhelming information volume when comprehending long-form documents. This challenge raises the imperative of a cohesive memory module, which can elevate vanilla LLMs into…