mlsanityData to 7 Oct 2026

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

arXiv 2410.12361 ↗First posted 16 Oct 2024cs.AI cs.CLcited by 84

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper, we tackle the challenge of developing proactive agents capable of anticipating and initiating tasks without explicit human instructions. We propose a novel data-driven approach for this problem. Firstly, we collect real-world human activities to generate proactive task predictions. These predictions are then labeled by human annotators as either accepted or rejected. The labeled data is used to train a reward model that simulates human judgment and serves as an automatic evaluator of the proactiveness of LLM agents. Building on this, we develop a comprehensive data generation pipeline to create a diverse dataset, ProactiveBench, containing 6,790 events. Finally, we demonstrate that fine-tuning models with the proposed ProactiveBench can significantly elicit the proactiveness of LLM agents. Experimental results show that our fine-tuned model achieves an F1-Score of 66.47% in proactively offering assistance, outperforming all open-source and close-source models. These results highlight the potential of our method in creating more proactive and effective agent systems, paving the way for future advancements in human-agent collaboration.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 19 of its 38 references that are in the map. First posted on arXiv 16 Oct 2024.

Builds on

19 of 38 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents14 Feb
  2. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security10 Jan
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 16

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Qwen Technical Reportcited by 3,273
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  9. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  10. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  11. 2023CogAgent: A Visual Language Model for GUI Agentscited by 692
  12. 2022PAL: Program-aided Language Modelscited by 635
4 more
  1. 2023Tool Learning with Foundation Modelscited by 302
  2. 2023Foundation Models in Robotics: Applications, Challenges, and the Futurecited by 212
  3. 2023WebCPM: Interactive Web Search for Chinese Long-form Question Answeringcited by 93
  4. 2023Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Modelcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 33; 2026: 51.

84 papers.

Sort:

By area:

  1. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 117
  2. 2025UserBench: An Interactive Gym Environment for User-Centric Agentscited by 69
  3. 2025ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptionscited by 44
  4. 2025Fully Autonomous AI Agents Should Not be Developedcited by 43
  5. 2025UserRL: Training Interactive User-Centric Agent via Reinforcement Learningcited by 27
  6. 2025Large Language Models Miss the Multi-Agent Markcited by 25
  7. 2025FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agentscited by 19
  8. 2026ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Datacited by 15
  9. 2025ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agentcited by 14
  10. 2026Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistantscited by 14
  11. 2025Position: The Real Barrier to LLM Agent Usability is Agentic ROIcited by 12
  12. 2025Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoCcited by 11
38 more
  1. 2025ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulationcited by 10
  2. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  3. 2025ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agentscited by 9
  4. 2025Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agentscited by 9
  5. 2025LLAMAPIE: Proactive In-Ear Conversation Assistantscited by 8
  6. 2025ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wildcited by 7
  7. 2026Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generationcited by 7
  8. 2026User as Code: Executable Memory for Personalized Agentscited by 7
  9. 2025Towards Evaluating Proactive Risk Awareness of Multimodal Language Modelscited by 6
  10. 2025OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?cited by 6
  11. 2025Agentic Services Computingcited by 6
  12. 2026Multi-User Large Language Model Agentscited by 6
  13. 2025AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistancecited by 5
  14. 2025Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challengescited by 5
  15. 2026ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devicescited by 5
  16. 2025YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Taskscited by 4
  17. 2025ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challengescited by 4
  18. 2026Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Modelscited by 4
  19. 2026GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Taskscited by 4
  20. 2026PreAct: Computer-Using Agents that Get Faster on Repeated Taskscited by 4
  21. 2025Interaction-Driven Browsing: A Human-in-the-Loop Conceptual Framework Informed by Human Web Browsing for Browser-Using Agentscited by 3
  22. 2025Overhearing LLM Agents: A Survey, Taxonomy, and Roadmapcited by 3
  23. 2026PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agentscited by 3
  24. 2026Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AIcited by 3
  25. 2026From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Benchcited by 3
  26. 2026ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agentscited by 3
  27. 2026Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agentscited by 3
  28. 2026Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systemscited by 3
  29. 2025Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approachcited by 2
  30. 2025Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agentscited by 2
  31. 2025LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialoguecited by 2
  32. 2026Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimizationcited by 2
  33. 2026ProAct: Harnessing Streaming Motion Generation and Agentic Reasoning for Real-Time Embodied Social Interactioncited by 2
  34. 2026Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insightcited by 2
  35. 2026PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agentcited by 2
  36. 2026Agentic Coding Needs Proactivity, Not Just Autonomycited by 2
  37. 2026Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?cited by 2
  38. 2026Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluationcited by 2

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response
  2. 2025Scaling Autonomous Agents via Automatic Reward Modeling And Planning
  3. 2026AgentAbstain: Do LLM Agents Know When Not to Act?
  4. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
  5. 2025Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs
  6. 2025AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress
  7. 2026Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention
  8. 2025Training Proactive and Personalized LLM Agents