Related papers: Semantic XPath: Structured Agentic Memory Access f…

Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models. In spite of these advantages, widespread adoption of these models for real-time conversational…

Conversational AI (CAI) systems offer opportunities to scale service provision to unprecedented levels and governments and corporations are already beginning to deploy them across services. The economic argument is similar across domains:…

As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely…

Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics. In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented…

In this paper, we present ConvoGen: an innovative framework for generating synthetic conversational data using multi-agent systems. Our method leverages few-shot learning and introduces iterative sampling from a dynamically updated few-shot…

Explainable AI (XAI) techniques aim to provide insights into predictive models and enhance user performance, yet they often fall short of these expectations. Conversational XAI assistants promise to overcome such limitations, but empirical…

Surveys and interviews are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. Recently, various domains have begun to…

Large Language Models demonstrate outstanding performance in many language tasks but still face fundamental challenges in managing the non-linear flow of human conversation. The prevalent approach of treating dialogue history as a flat,…

Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and…

Discourse structure is integral to understanding a text and is helpful in many NLP tasks. Learning latent representations of discourse is an attractive alternative to acquiring expensive labeled discourse data. Liu and Lapata (2018) propose…

We introduce a tree-structured attention neural network for sentences and small phrases and apply it to the problem of sentiment classification. Our model expands the current recursive models by incorporating structural information around a…

In a conversational context, a user expresses her multi-faceted information need as a sequence of natural-language questions, i.e., utterances. Starting from a given topic, the conversation evolves through user utterances and system…

Recent advancements in large language models have significantly improved their context windows, yet challenges in effective long-term memory management remain. We introduce MemTree, an algorithm that leverages a dynamic, tree-structured…

Existing retrieval methods in Large Language Models show degradation in accuracy when handling temporally distributed conversations, primarily due to their reliance on simple similarity-based retrieval. Unlike existing memory retrieval…

The emergence of capable large language model (LLM) based agents necessitates memory architectures that transcend mere data storage, enabling continuous learning, nuanced reasoning, and dynamic adaptation. Current memory systems often…

AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural…

Predicting user satisfaction in conversational systems has become critical, as spoken conversational assistants operate in increasingly complex domains. Online satisfaction prediction (i.e., predicting satisfaction of the user with the…

The structured representation for semantic parsing in task-oriented assistant systems is geared towards simple understanding of one-turn queries. Due to the limitations of the representation, the session-based properties such as…

Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their high computational overhead, many approaches build such…

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…