Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation
cs.AI
Submitted: 2026-09-03
Updated: 2026-09-03
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Attention-Sensitive Alerting
- ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
- PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
- Proactive Systems in HCI and AI: Concepts, Challenges, and Opportunities
- Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
- Levels of Autonomy for AI Agents
- Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
- PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents
- AI for Service: Proactive Assistance with AI Glasses
- Hybrid Self-evolving Structured Memory for GUI Agents
- When not to help: planning for lasting human-AI collaboration
- Sotopia-RL: Reward Design for Social Intelligence
- UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
- Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
- Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks
- Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems
- When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation
- Should I send this notification? Optimizing push notifications decision making by modeling the future
- ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
- Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection