相关论文: State Contamination in Memory-Augmented LLM Agents

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of disconnected events. This lack of temporal awareness facilitates a "Safety Gap" where…

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Memory management is vital for LLM agents to handle long-term interaction and personalization. Most research focuses on how to organize and use memory summary, but often overlooks the initial memory extraction stage. In this paper, we argue…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficient and flexible agent collaboration. However, moving coordination into latent space may…

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities…

Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, this memory mechanism also creates a practical security…

Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful…

Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large Language Models (LLMs) facilitate the construction and deployment of agents. Different memory…

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate…

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…

Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new…

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…

Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumulating risk prior to escalation. In real-world care, however, clinicians act on gradually…

Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the…

When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the next attempt and elevating the per-step error rate beyond the base level. This…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…