Proactive Dialogue Policy Optimization via Cognitive-State Transition
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/volcengine/verl2https:
Sources
- COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
- Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback
- LoRA: Low-Rank Adaptation of Large Language Models
- DiscoverLLM: From Executing Intents to Discovering Them
- Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
- Cognitive World Model for Progressive BDI/E Trajectory Evaluation of Conversational Agents
- Playing Atari with Deep Reinforcement Learning
- Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants
- HumanLM: Simulating Users with State Alignment Beats Response Imitation
- Unlocking Proactivity in Task-Oriented Dialogue
- UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems