Related papers: Asymmetric Goal Drift in Coding Agents Under Value…
An information owner, possessing diverse data sources, might want to offer information services based on these sources to cooperation partners and to this end interact with these partners by receiving and sending messages, which the owner…
Control-flow hijacking attacks manipulate orchestration mechanisms in multi-agent systems into performing unsafe actions that compromise the system and exfiltrate sensitive information. Recently proposed defenses, such as LlamaFirewall,…
Implementation security, higher generation rate, and lower cost are primary missions in the domain of quantum key distributions in recent years. However, simultaneously achieving robust security, high speed, and low cost often resembles an…
Coordinating multiple autonomous agents to reach a target region while avoiding collisions and maintaining communication connectivity is a core problem in multi-agent systems. In practice, agents have a limited communication range. Thus,…
Educational dialogue is critical for decoding student learning processes, yet manual annotation remains time-consuming. This study evaluates the efficacy of GPT-5.2 and Gemini-3 using three prompting strategies (few-shot, single-agent, and…
Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by reinforcing the correct goals, but alignment may not always succeed and can lead to unwanted side…
Autonomous traffic agents (ATAs) are expected to act in ways tat are not only safe, but also aligned with stakeholder values across legal, social, and moral dimensions. In this paper, we adopt an established formal model of conflict from…
Legal compliance in AI-driven data transfer planning is becoming increasingly critical under stringent privacy regulations such as the Japanese Act on the Protection of Personal Information (APPI). We propose a multi-agent legal verifier…
Qualitative analysis plays a pivotal role in understanding the human and social aspects of software engineering. However, it remains a demanding process shaped by the subjective interpretation of individual researchers and sensitive to…
Safe planning of an autonomous agent in interactive environments -- such as the control of a self-driving vehicle among pedestrians -- poses a major challenge as the behavior of the environment is unknown and reactive to the behavior of the…
AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…
Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…
Multi-agent coordination problems often require agents to exchange state information in order to reach some collective goal, such as agreement on a final state value. In some cases, it is feasible that opportunistic agents may deceptively…
Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often…
Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches…
Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge…
We investigate the Free Energy Principle as a foundation for measuring risk in agentic and multi-agent systems. From these principles we introduce a Cumulative Risk Exposure metric that is flexible to differing contexts and needs. We…
The study addressed the problem of Anonymous Multi-Agent Path-finding (AMAPF). Unlike the classical formulation, where the assignment of agents to goals is fixed, in the anonymous MAPF setting it is irrelevant which agent reaches specific…
Recent advances in AI-assisted education have encouraged the integration of vision-language models (VLMs) into academic assessment, particularly for tasks that require both quantitative and qualitative evaluation. However, existing VLM…
As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are…