Related papers: MEEP: An Open-Source Platform for Human-Human Dial…
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are…
Most conversational agents (CAs) are designed to satisfy user needs through user-driven interactions. However, many real-world settings, such as academic interviewing, judicial proceedings, and journalistic investigations, involve broader…
We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, discuss topics and situations,…
End-to-end task bots are typically learned over a static and usually limited-size corpus. However, when deployed in dynamic, changing, and open environments to interact with users, task bots tend to fail when confronted with data that…
Functionality and dialogue experience are two important factors of task-oriented dialogue systems. Conventional approaches with closed schema (e.g., conversational semantic parsing) often fail as both the functionality and dialogue…
End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating. However, current end-to-end approaches only consider user semantic inputs in learning and under-utilize…
End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task. While in non-collaborative settings, for example, negotiation and…
Machine-learning based dialogue managers are able to learn complex behaviors in order to complete a task, but it is not straightforward to extend their capabilities to new domains. We investigate different policies' ability to handle…
In recent years, artificial intelligence has developed in a variety of fields and is now integrated into many aspects of our daily lives. This includes AI speakers,communication robots, and other interactive systems. We are interested in AI…
While many tools are available for designing AI, non-experts still face challenges in clearly expressing their intent and managing system complexity. We introduce AIAP, a no-code platform that integrates natural language input with visual…
Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…
There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI. Unlike traditional…
Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation,…
Language-guided Embodied AI benchmarks requiring an agent to navigate an environment and manipulate objects typically allow one-way communication: the human user gives a natural language command to the agent, and the agent can only follow…
Novel end-user programming (EUP) tools enable on-the-fly (i.e., spontaneous, easy, and rapid) creation of interactions with robotic systems. These tools are expected to empower users in determining system behavior, although very little is…
Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However, current powerful agents often depend on sophisticated prompt…
Recent improvements in large language models (LLMs) have had a dramatic effect on capabilities and productivity across many disciplines involving critical thinking and writing. The development of the model context protocol (MCP) provides a…
Response timing judgment is a critical component of interactive speech agents. Although there exists substantial prior work on turn modeling and voice wake-up, there is a lack of research on response timing judgments continuously aligned…
Training task-oriented dialogue systems is both costly and time-consuming, due to the need for high-quality datasets encompassing diverse intents. Traditional methods depend on extensive human annotation, while recent advancements leverage…
Embodied agents struggle to generalize to new environments, even when those environments share similar underlying structures to their training settings. Most current approaches to generating these training environments follow an open-loop…