{"total":75,"rows":[{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402,"area":"agents"},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627,"area":null},{"id":"2111.14592","title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","created":"2021-11-29","cited_by_count":102,"area":null},{"id":"2305.03010","title":"Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence","created":"2023-05-04","cited_by_count":81,"area":null},{"id":"2305.13040","title":"SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents","created":"2023-05-22","cited_by_count":71,"area":"agents"},{"id":"2106.02787","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","created":"2021-06-05","cited_by_count":56,"area":null},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38,"area":null},{"id":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34,"area":null},{"id":"2401.05033","title":"Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk","created":"2024-01-10","cited_by_count":34,"area":"agents"},{"id":"2204.07667","title":"Just Fine-tune Twice: Selective Differential Privacy for Large Language Models","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2209.06638","title":"SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding","created":"2022-09-14","cited_by_count":28,"area":null},{"id":"2207.14627","title":"\"Do you follow me?\": A Survey of Recent Approaches in Dialogue State Tracking","created":"2022-07-29","cited_by_count":22,"area":null},{"id":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":22,"area":null},{"id":"2407.09522","title":"UQE: A Query Engine for Unstructured Databases","created":"2024-06-23","cited_by_count":21,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2204.07299","title":"Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals","created":"2022-04-15","cited_by_count":12,"area":null},{"id":"2205.11690","title":"Workflow Discovery from Dialogues in the Low Data Regime","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2205.04515","title":"Unsupervised Slot Schema Induction for Task-oriented Dialog","created":"2022-05-09","cited_by_count":11,"area":null},{"id":"2403.05766","title":"FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs","created":"2024-03-09","cited_by_count":11,"area":null},{"id":"2409.14195","title":"The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends","created":"2024-09-21","cited_by_count":11,"area":null},{"id":"2112.08342","title":"DG2: Data Augmentation Through Document Grounded Dialogue Generation","created":"2021-12-15","cited_by_count":10,"area":null},{"id":"2212.09939","title":"AnyTOD: A Programmable Task-Oriented Dialog System","created":"2022-12-20","cited_by_count":10,"area":null},{"id":"2304.12982","title":"Intent Induction from Conversations for Task-Oriented Dialogue Track at DSTC 11","created":"2023-04-25","cited_by_count":10,"area":null},{"id":"2311.10785","title":"Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Models","created":"2023-11-16","cited_by_count":10,"area":null},{"id":"2503.17509","title":"Follow-up Question Generation For Enhanced Patient-Provider Conversations","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2211.11617","title":"CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation","created":"2022-11-21","cited_by_count":9,"area":null},{"id":"2410.18481","title":"Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction","created":"2024-10-24","cited_by_count":8,"area":null},{"id":"2505.19978","title":"DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2601.22027","title":"CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2204.01061","title":"Task2Dial: A Novel Task and Dataset for Commonsense enhanced Task-based Dialogue Grounded in Documents","created":"2022-04-03","cited_by_count":7,"area":null},{"id":"2302.05932","title":"Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking","created":"2023-02-12","cited_by_count":6,"area":null},{"id":"2304.01412","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2307.12425","title":"On the Effectiveness of Offline RL for Dialogue Response Generation","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2205.07352","title":"Long-term Control for Dialogue Generation: Methods and Evaluation","created":"2022-05-15","cited_by_count":5,"area":null},{"id":"2205.12244","title":"Unsupervised Learning of Hierarchical Conversation Structure","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2305.03007","title":"NatCS: Eliciting Natural Customer Support Dialogues","created":"2023-05-04","cited_by_count":5,"area":null},{"id":"2307.07047","title":"Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues?","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2502.17321","title":"Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2506.00178","title":"Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2510.21244","title":"VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series","created":"2025-10-24","cited_by_count":5,"area":"agents"},{"id":"2205.14748","title":"Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition","created":"2022-05-29","cited_by_count":4,"area":null},{"id":"2306.01729","title":"Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2309.11065","title":"UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2406.15214","title":"Unsupervised Extraction of Dialogue Policies from Conversations","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2507.19543","title":"Agent WARPP: Workflow Adherence via Runtime Parallel Personalization","created":"2025-07-23","cited_by_count":3,"area":"agents"},{"id":"2603.28569","title":"CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments","created":"2026-03-30","cited_by_count":3,"area":"agents"},{"id":"2605.24900","title":"ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents","created":"2026-05-24","cited_by_count":3,"area":"lr"},{"id":"2311.09593","title":"Multi-Step Dialogue Workflow Action Prediction","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2504.17390","title":"PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2511.15976","title":"TOD-ProcBench: Benchmarking Complex Instruction-Following in Task-Oriented Dialogues","created":"2025-11-20","cited_by_count":2,"area":null},{"id":"2607.01426","title":"When Should Service Agents Reconsider? Difficulty-Routed Control in Customer-Service Operations","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2208.12886","title":"Building the Intent Landscape of Real-World Conversational Corpora with Extractive Question-Answering Transformers","created":"2022-08-26","cited_by_count":1,"area":null},{"id":"2212.02745","title":"Sources of Noise in Dialogue and How to Deal with Them","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2307.07255","title":"Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems","created":"2023-07-14","cited_by_count":1,"area":"agents"},{"id":"2309.13448","title":"Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2410.14853","title":"DFlow: Diverse Dialogue Flow Simulation with Large Language Models","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2411.02448","title":"Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models","created":"2024-11-03","cited_by_count":1,"area":null},{"id":"2509.23246","title":"Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2603.16783","title":"SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.17217","title":"Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2607.22635","title":"CallBench: A Benchmark for Dual-Goal Coordination in Phone Call Assistants","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2609.18126","title":"Designing Agentic AI Workflow Portfolios under Imperfect Selection and Compute Cost","created":"2026-09-16","cited_by_count":1,"area":"agents"},{"id":"2609.30706","title":"LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2208.07597","title":"Manual-Guided Dialogue for Flexible Conversational Agents","created":"2022-08-16","cited_by_count":0,"area":null},{"id":"2306.03959","title":"Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2404.08155","title":"Graph Integrated Language Transformers for Next Action Prediction in Complex Phone Calls","created":"2024-04-11","cited_by_count":0,"area":null},{"id":"2502.12458","title":"An Empirical Evaluation of Encoder Architectures for Fast Real-Time Long Conversational Understanding","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2507.13544","title":"A Computational Approach to Modeling Conversational Systems: Analyzing Large-Scale Quasi-Patterned Dialogue Flows","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2603.23172","title":"From Synthetic to Native: Benchmarking Multilingual Intent Classification in Logistics Customer Service","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2607.24768","title":"PATHFinder Agent for Tailored Prenatal Care","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.00330","title":"Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.00434","title":"SAGE: State-Grounded, Abstention-Aware Evaluation of Task-Oriented Dialogue Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2610.02460","title":"CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.18881","title":"Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":null}