Related papers: State Contamination in Memory-Augmented LLM Agents

Large Language Model (LLM) agents are deployed in complex environments -- such as massive codebases, enterprise databases, and conversational histories -- where the relevant state far exceeds their context windows. To navigate these spaces,…

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…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

Agent memory failures are silent: an LLM-based agent can produce a fluent response even when it fails to extract, retain, or retrieve the information needed across sessions. The write-manage-read loop describes the external pipeline of…

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…

Existing backdoor attacks on Large Language Model-based agents remain stateless, executing fixed behaviors confined to a single session. We propose a stateful agent backdoor that extends the attack lifecycle across multiple sessions under…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems. This evolution stems from empowering LLMs with additional modules such…

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…

The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of…

Under a unified operational definition, we define LLM memory as a persistent state written during pretraining, finetuning, or inference that can later be addressed and that stably influences outputs. We propose a four-part taxonomy…

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…

Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…

Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them to address complex challenges. However, within these multi-agent systems, the…

Large language models (LLMs) are equipped with safety mechanisms to detect and block harmful queries, yet current alignment approaches primarily focus on overtly dangerous content and overlook more subtle threats. However, users can often…

Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…

Contemporary approaches to agent-based modeling (ABM) of social systems have traditionally emphasized rule-based behaviors, limiting their ability to capture nuanced dynamics by moving beyond predefined rules and leveraging contextual…