Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/openclaw/openclaw
Project page: https://harryoh99.github.io/foundations_of_proactive_agents/1
Sources
- Agentic Coding Needs Proactivity, Not Just Autonomy
- KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation
- ProactBench: Beyond What The User Asked For
- Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents
- Gemma 3 Technical Report
- ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices
- Sleep-time Compute: Beyond Inference Scaling at Test-time
- Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass Correlation
- Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
- Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
- Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
- OpenJarvis: Personal AI, On Personal Devices
- Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation
- ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data
- Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC
- VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
- Qwen3 Technical Report
- Designing Proactive Thought Partners for Writing
- $\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
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