Related papers: Dual-Agent Co-Training for Health Coaching via Imp…

Large language models (LLMs) have had a significant impact on diverse research domains, including medicine and healthcare. However, the potential of LLMs as copilots in medical education remains underexplored. Current AI-assisted…

Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a greedy learning strategy that aims to maximize its own reward may fall into a local optimum.…

Multi-turn human-AI collaboration is fundamental to deploying interactive services such as adaptive tutoring, conversational recommendation, and professional consultation. However, optimizing these interactions via reinforcement learning is…

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

The cooperation among AI systems, and between AI systems and humans is becoming increasingly important. In various real-world tasks, an agent needs to cooperate with unknown partner agent types. This requires the agent to assess the…

Virtual coaching has rapidly evolved into a foundational component of modern clinical practice. At a time when healthcare professionals are in short supply and the demand for low-cost treatments is ever-increasing, virtual health coaches…

While the advancement of large language models has spurred the development of AI agents to automate tasks, numerous use cases inherently require agents to collaborate with humans due to humans' latent preferences, domain expertise, or the…

Assistive agents should not only take actions on behalf of a human, but also step out of the way and cede control when there are important decisions to be made. However, current methods for building assistive agents, whether via mimicking…

Young people's mental well-being is a global concern, with peer support playing a key role in daily emotional regulation. Conversational agents are increasingly viewed as promising tools for delivering accessible, personalised peer support,…

In multi-agent reinforcement learning, the cooperative learning behavior of agents is very important. In the field of heterogeneous multi-agent reinforcement learning, cooperative behavior among different types of agents in a group is…

Multi-agent AI systems, which simulate diverse instructional roles such as teachers and peers, offer new possibilities for personalized and interactive learning. Yet, student-AI interaction patterns and their pedagogical implications remain…

Existing benchmarks for conversational AI agents simulate single-control environments, where only the AI agent can use tools to interact with the world, while the user remains a passive information provider. This differs from real-world…

Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment. While in real-world scenarios,…

Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which…

The integration of artificial intelligence across multiple domains has emphasized the importance of replicating human-like cognitive processes in AI. By incorporating emotional intelligence into AI agents, their emotional stability can be…

Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving contexts and strategically adapting opponents. Such environments are inherently…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced…

Existing language agents often encounter difficulties in dynamic adversarial games due to poor strategic reasoning. To mitigate this limitation, a promising approach is to allow agents to learn from game interactions automatically, without…