Chatbots have become one of the main pathways for the delivery of business automation tools. Multi-agent systems offer a framework for designing chatbots at scale, making it easier to support complex conversations that span across multiple domains as well as enabling developers to maintain and expand their capabilities incrementally over time. However, multi-agent systems complicate the natural language understanding (NLU) of user intents, especially when they rely on decentralized NLU models: some utterances (termed single intent) may invoke a single agent while others (termed multi-intent) may explicitly invoke multiple agents. Without correctly parsing multi-intent inputs, decentralized NLU approaches will not achieve high prediction accuracy. In this paper, we propose an efficient parsing and orchestration pipeline algorithm to service multi-intent utterances from the user in the context of a multi-agent system. Our proposed approach achieved comparable performance to competitive deep learning models on three different datasets while being up to 48 times faster.

Teaching task-level directives to robots via demonstration is a popular tool to expand the robot's capabilities to interact with its environment. While current learning from demonstration systems primarily focuses on abstracting the task-level knowledge to the robot, these systems lack the ability to understand which part of the task can be already solved given the robot's prior knowledge. Therefore, instead of only requiring demonstrations of the missing pieces, these systems will require a demonstration of the complete task, which is cumbersome, repetitive, and can discourage people from helping the robot by performing the demonstrations. Therefore, we propose to use the notion of "excuses" to identify the smallest change in the robot state that makes a task, currently not solvable by the robot, solvable -- as a means to solicit more targeted demonstrations from a human. These excuses are generated automatically using combinatorial search over possible changes that can be made to the robot's state and choosing the minimum changes that make it solvable. These excuses then serve as guidance for the demonstrator who can use it to decide what to demonstrate to the robot in order to make this requested change possible, thereby making the original task solvable for the robot without having to demonstrate it in its entirety. By working with symbolic state descriptions, the excuses can be directly communicated and intuitively understood by a human demonstrator. We show empirically and in a user study that the use of excuses reduces the demonstration time by 54% and leads to a 74% reduction in demonstration size.

This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this sangam, we explore two different flavors of model space problems that have been studied in the AI planning literature and explore the effect of an LLM on those tasks. We empirically demonstrate how the performance of an LLM contrasts with combinatorial search (CS) - an approach that has been traditionally used to solve model space tasks in planning, both with the LLM in the role of a standalone model space reasoner as well as in the role of a statistical signal in concert with the CS approach as part of a two-stage process. Our experiments show promising results suggesting further forays of LLMs into the exciting world of model space reasoning for planning tasks in the future.

Existing approaches for the design of interpretable agent behavior consider different measures of interpretability in isolation. In this paper we posit that, in the design and deployment of human-aware agents in the real world, notions of interpretability are just some among many considerations; and the techniques developed in isolation lack two key properties to be useful when considered together: they need to be able to 1) deal with their mutually competing properties; and 2) an open world where the human is not just there to interpret behavior in one specific form. To this end, we consider three well-known instances of interpretable behavior studied in existing literature -- namely, explicability, legibility, and predictability -- and propose a revised model where all these behaviors can be meaningfully modeled together. We will highlight interesting consequences of this unified model and motivate, through results of a user study, why this revision is necessary.

A new design of an AI assistant that has become increasingly popular is that of an "aggregated assistant" - realized as an orchestrated composition of several individual skills or agents that can each perform atomic tasks. In this paper, we will talk about the role of planning in the automated composition of such assistants and explore how concepts in automated planning can help to establish transparency of the inner workings of the assistant to the end-user. Conversational assistants such as Siri, Google Assistant, Figure 1: Simplified architecture diagram of Verdi (Rizk et and Alexa have found increased user adoption over the last al.

Designing robots capable of generating interpretable behavior is a prerequisite for achieving effective human-robot collaboration. This means that the robots need to be capable of generating behavior that aligns with human expectations and, when required, provide explanations to the humans in the loop. However, exhibiting such behavior in arbitrary environments could be quite expensive for robots, and in some cases, the robot may not even be able to exhibit the expected behavior. Given structured environments (like warehouses and restaurants), it may be possible to design the environment so as to boost the interpretability of the robot's behavior or to shape the human's expectations of the robot's behavior. In this paper, we investigate the opportunities and limitations of environment design as a tool to promote a type of interpretable behavior -- known in the literature as explicable behavior. We formulate a novel environment design framework that considers design over multiple tasks and over a time horizon. In addition, we explore the longitudinal aspect of explicable behavior and the trade-off that arises between the cost of design and the cost of generating explicable behavior over a time horizon.

In this survey, we study how recent advances in machine intelligence are disrupting the world of business processes. Over the last decade, there has been steady progress towards the automation of business processes under the umbrella of ``robotic process automation'' (RPA). However, we are currently at an inflection point in this evolution, as a new paradigm called ``Intelligent Process Automation'' (IPA) emerges, bringing machine learning (ML) and artificial intelligence (AI) technologies to bear in order to improve business process outcomes. The purpose of this paper is to provide a survey of this emerging theme and identify key open research challenges at the intersection of AI and business processes. We hope that this emerging theme will spark engaging conversations at the RPA Forum.

This paper reports on the open source project CLAI (Command Line AI), aimed at bringing the power of AI to the command line interface. The platform sets up the CLI as a new environment for AI researchers to conquer by surfacing the command line as a generic environment that researchers can interface to using a simple sense-act API much like the traditional AI agent architecture. In this paper, we discuss the design and implementation of the platform in detail, through illustrative use cases of new end user interaction patterns enabled by this design, and through quantitative evaluation of the system footprint of a CLAI-enabled terminal. We also report on some early user feedback on its features from an internal survey.

The semantics of this compilation is that by invoking the service the planner is expecting to get back (n)one or more of the promised outputs. Composition T echnique The inputs to the composition step is thus a process and a set of skills and the output is a optimized process wherein the original process has been composed with skills wherever possible to maximize automation, as shown in Figure 3. Once the skills have been compiled to the standard D3WA form the rest of the process remains same as in D3WA. This means we get all the rest of its features for free, including being able to visualize, debug, and iterate on the composed process once it has been computed. Specifically with regards to business process management, we illustrate some key capabilities next. The reason declarative works well in this setting is twofold: First, the sheer size of these composed processes, and the need to be able to be flexible with their management, makes it imperative that they are not written and maintained by hand. Furthermore, as we mentioned before, the source of skills and processes may be different. The declarative framework allows developers of either to develop without having to worry about how they relate to each other.

Generating complex multi-turn goal-oriented dialogue agents is a difficult problem that has seen a considerable focus from many leaders in the tech industry, including IBM, Google, Amazon, and Microsoft. This is in large part due to the rapidly growing market demand for dialogue agents capable of goal-oriented behaviour. Due to the business process nature of these conversations, end-to-end machine learning systems are generally not a viable option, as the generated dialogue agents must be deployable and verifiable on behalf of the businesses authoring them. In this work, we propose a paradigm shift in the creation of goal-oriented complex dialogue systems that dramatically eliminates the need for a designer to manually specify a dialogue tree, which nearly all current systems have to resort to when the interaction pattern falls outside standard patterns such as slot filling. We propose a declarative representation of the dialogue agent to be processed by state-of-the-art planning technology. Our proposed approach covers all aspects of the process; from model solicitation to the execution of the generated plans/dialogue agents. Along the way, we introduce novel planning encodings for declarative dialogue synthesis, a variety of interfaces for working with the specification as a dialogue architect, and a robust executor for generalized contingent plans. We have created prototype implementations of all components, and in this paper, we further demonstrate the resulting system empirically.