Imagen de Portada

Safety as Computation: Certified Answer Reuse via Capability Closure in Task-Oriented Dialogue

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Spera, Cosimo
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From Workflow Automation to Capability Closure: A Formal Framework for Safe and Revenue-Aware Customer Service AI
por: Spera, Cosimo
Publicado: (2026)

Capability Safety as Datalog: A Foundational Equivalence
por: Spera, Cosimo
Publicado: (2026)

Safety is Non-Compositional: A Formal Framework for Capability-Based AI Systems
por: Spera, Cosimo
Publicado: (2026)

Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations
por: Agrawal, Garima, et al.
Publicado: (2024)

Reversing the Paradigm: Building AI-First Systems with Human Guidance
por: Spera, Cosimo, et al.
Publicado: (2025)

Unlocking Proactivity in Task-Oriented Dialogue
por: Zhang, Hongbin, et al.
Publicado: (2026)

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
por: Zhang, Ming, et al.
Publicado: (2024)

Redefining CX with Agentic AI: Minerva CQ Case Study
por: Agrawal, Garima, et al.
Publicado: (2025)

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk
por: Ulmer, Dennis, et al.
Publicado: (2024)

Towards Automatic Evaluation of Task-Oriented Dialogue Flows
por: Mirtaheri, Mehrnoosh, et al.
Publicado: (2024)

Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
por: Xu, Jingyi, et al.
Publicado: (2026)

Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
por: Du, Huifang, et al.
Publicado: (2024)

Using Medical Algorithms for Task-Oriented Dialogue in LLM-Based Medical Interviews
por: Reis, Rui, et al.
Publicado: (2025)

TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
por: Acikgoz, Emre Can, et al.
Publicado: (2025)

LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning
por: Zhu, Yu, et al.
Publicado: (2026)

HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals
por: Mo, Lingbo, et al.
Publicado: (2024)

Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
por: Yoon, Yejin, et al.
Publicado: (2025)

Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems
por: Kazi, Taaha, et al.
Publicado: (2024)

Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues
por: Ou, Jiao, et al.
Publicado: (2024)

DiagGPT: An LLM-based and Multi-agent Dialogue System with Automatic Topic Management for Flexible Task-Oriented Dialogue
por: Cao, Lang
Publicado: (2023)

ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
por: Zhang, Yifei, et al.
Publicado: (2026)

Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems
por: Ohashi, Atsumoto, et al.
Publicado: (2025)

Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue
por: Park, Jeiyoon, et al.
Publicado: (2022)

Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings
por: Elizabeth, Michelle, et al.
Publicado: (2024)

Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests
por: Mannekote, Amogh, et al.
Publicado: (2024)

Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues
por: Medjad, Maya, et al.
Publicado: (2025)

JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset
por: Ohashi, Atsumoto, et al.
Publicado: (2024)

DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues
por: Luo, Xiang, et al.
Publicado: (2024)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
por: Cao, Chentao, et al.
Publicado: (2025)

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
por: Si, Shuzheng, et al.
Publicado: (2023)

Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Experts
por: Su, Ruolin, et al.
Publicado: (2024)

Decision-Oriented Dialogue for Human-AI Collaboration
por: Lin, Jessy, et al.
Publicado: (2023)

Discovering Novel LLM Experts via Task-Capability Coevolution
por: Dai, Andrew, et al.
Publicado: (2026)

STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media
por: Xue, Liang, et al.
Publicado: (2026)

Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance
por: Wang, Yufeng, et al.
Publicado: (2025)

Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning
por: Prajapat, Dharmendra, et al.
Publicado: (2024)

Continual Robot Skill and Task Learning via Dialogue
por: Gu, Weiwei, et al.
Publicado: (2024)

MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues
por: Xue, Liang, et al.
Publicado: (2025)

Scalable Task Planning via Large Language Models and Structured World Representations
por: Pérez-Dattari, Rodrigo, et al.
Publicado: (2024)

First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models
por: Fu, Chuanruo, et al.
Publicado: (2025)