Introduces a Cognitive User Simulator modeling stratified personas with hidden concerns and Simulator-Induced Asymmetric-View Policy Optimization to unlock proactive behavior in task-oriented dialogue agents.
Mixed citations
Multiwoz-a large-scale multi- domain wizard-of-oz dataset for task-oriented dialogue mod- elling
Mixed citation behavior. Most common role is background (60%).
7
Pith papers citing it
4
external citations · external index
Background
60% of classified citations
citation-role summary
background 3
method 2
citation-polarity summary
verdicts
UNVERDICTED 7representative citing papers
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
τ²-bench provides a Dec-POMDP-based telecom domain with compositional task generation and a tool-constrained user simulator to measure agent performance drops in dual-control versus single-control settings.
τ-bench shows state-of-the-art agents like GPT-4o succeed on under 50% of tool-using, rule-following tasks and are inconsistent across repeated trials.
A dual hierarchical RL framework with two agents coordinates high-level dialogue strategy and low-level question generation to emulate judicial questioning and extract key information from Supreme Court arguments, outperforming baselines.
GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.
The authors define a universal dialogue act schema, align several task-oriented dialogue datasets to it, and report a tagger reaching 54.1% F1 unsupervised and 57.7% semi-supervised on human-human dialogues.
citing papers explorer
-
Unlocking Proactivity in Task-Oriented Dialogue
Introduces a Cognitive User Simulator modeling stratified personas with hidden concerns and Simulator-Induced Asymmetric-View Policy Optimization to unlock proactive behavior in task-oriented dialogue agents.
-
SAGE: A Service Agent Graph-guided Evaluation Benchmark
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
-
$\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
τ²-bench provides a Dec-POMDP-based telecom domain with compositional task generation and a tool-constrained user simulator to measure agent performance drops in dual-control versus single-control settings.
-
$\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
τ-bench shows state-of-the-art agents like GPT-4o succeed on under 50% of tool-using, rule-following tasks and are inconsistent across repeated trials.
-
Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents
A dual hierarchical RL framework with two agents coordinates high-level dialogue strategy and low-level question generation to emulate judicial questioning and extract key information from Supreme Court arguments, outperforming baselines.
-
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.
-
Towards Universal Dialogue Act Tagging for Task-Oriented Dialogues
The authors define a universal dialogue act schema, align several task-oriented dialogue datasets to it, and report a tagger reaching 54.1% F1 unsupervised and 57.7% semi-supervised on human-human dialogues.