相关论文: From Static Context to Calibrated Interactive RL: …

The rapid evolution of Large Language Models (LLMs) has accelerated the transition from conversational chatbots to general agents. However, effectively balancing empathetic communication with budget-aware decision-making remains an open…

We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not…

Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn actions. Large language models (LLMs) can infer such constraints but are unreliable over long…

Multi-turn conversation has emerged as a predominant interaction paradigm for Large Language Models (LLMs). Users often employ follow-up questions to refine their intent, expecting LLMs to adapt dynamically. However, recent research reveals…

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables…

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement…

As Large Language Models (LLMs) get integrated into diverse workflows, they are increasingly being regarded as "collaborators" with humans, and required to work in coordination with other AI systems. If such AI collaborators are to reliably…

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

A robot's deployment environment often involves perceptual changes that differ from what it has experienced during training. Standard practices such as data augmentation attempt to bridge this gap by augmenting source images in an effort to…

Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the user's current message and more shaped by prior interaction history, while still appearing…

This paper proposes a reinforcement learning (RL)-based backstepping control strategy to achieve fixed time consensus in nonlinear multi-agent systems with strict feedback dynamics. Agents exchange only output information with their…

Large language models (LLMs) demonstrate strong reasoning abilities across mathematical, strategic, and linguistic tasks, yet little is known about how well they reason in dynamic, real-time, multi-agent scenarios, such as collaborative…

Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning. While previous studies have extensively examined biases related to protected attributes such…

AI-based persona simulation -- often referred to as digital twin simulation -- is increasingly used for market research, recommender systems, and social sciences. Despite their flexibility, large language models (LLMs) often exhibit…

Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe content, and a tendency…

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the…

In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the…

As user simulators are increasingly used for interactive training and evaluation of AI assistants, it is essential that they represent the diverse behaviors of real users. While existing works train user simulators to generate human-like…

Interactive reinforcement learning (IRL) extends traditional reinforcement learning (RL) by allowing an agent to interact with parent-like trainers during a task. In this paper, we present an IRL approach using dynamic audio-visual input in…