Related papers: Why Agents Compromise Safety Under Pressure
The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…
As autonomous agents become more prevalent, understanding their collective behaviour in strategic interactions is crucial. This study investigates the emergent cooperative tendencies of systems of Large Language Model (LLM) agents in a…
Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…
Agentic systems powered by large language models (LLMs) are becoming progressively more complex and capable. Their increasing agency and expanding deployment settings attract growing attention to effective governance policies, monitoring,…
Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across…
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure…
Agent-based modeling and simulation has evolved as a powerful tool for modeling complex systems, offering insights into emergent behaviors and interactions among diverse agents. Integrating large language models into agent-based modeling…
Clinical dialogue represents a complex duality requiring both the empathetic fluency of natural conversation and the rigorous precision of evidence-based medicine. While Large Language Models possess unprecedented linguistic capabilities,…
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…
Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…
As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…
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…
As large language models (LLMs) are increasingly deployed as autonomous agents, understanding their cooperation and social mechanisms is becoming increasingly important. In particular, how LLMs balance self-interest and collective…
The enhanced capabilities of LLM-based agents come with an emergency for model planning and tool-use abilities. Attributing to helpful-harmless trade-off from LLM alignment, agents typically also inherit the flaw of "over-refusal", which is…
In recent years, agents have become capable of communicating seamlessly via natural language and navigating in environments that involve cooperation and competition, a fact that can introduce social dilemmas. Due to the interleaving of…
Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…
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…
Conflicts between user preferences and automated system behavior already shape the experience of automated mobility. For example, a passenger may prefer assertive driving, yet the vehicle slows down early to follow a conservative policy or…
Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…
As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and…