# Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation arXiv: https://arxiv.org/abs/2609.03727 ยท HTML: https://mlsanity.com/paper/2609.03727/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 79 of its 100 references that are in the map. - First posted on arXiv 3 Sep 2026. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 30 of 79) - [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023) - [Doubly Robust Off-policy Value Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1511.03722/) (2015) - [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021) - [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025) - [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020) - [Asking Clarifying Questions in Open-Domain Information-Seeking Conversations](https://mlsanity.com/paper/1907.06554/) (2019) - [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023) - [Optimal and Adaptive Off-policy Evaluation in Contextual Bandits](https://mlsanity.com/paper/1612.01205/) (2016) - [Towards Conversational Recommendation over Multi-Type Dialogs](https://mlsanity.com/paper/2005.03954/) (2020) - [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024) - [Towards Topic-Guided Conversational Recommender System](https://mlsanity.com/paper/2010.04125/) (2020) - [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020) - [Proactive Human-Machine Conversation with Explicit Conversation Goals](https://mlsanity.com/paper/1906.05572/) (2019) - [Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance](https://mlsanity.com/paper/2410.12361/) (2024) - [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023) - [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024) - [Target-Guided Open-Domain Conversation](https://mlsanity.com/paper/1905.11553/) (2019) - [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023) - [Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions](https://mlsanity.com/paper/2109.05794/) (2021) - [Towards Human-centered Proactive Conversational Agents](https://mlsanity.com/paper/2404.12670/) (2024) - [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025) - [DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation](https://mlsanity.com/paper/2109.08877/) (2021) - [ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions](https://mlsanity.com/paper/2505.14668/) (2025) - [Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering](https://mlsanity.com/paper/2502.13069/) (2025) - [Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling](https://mlsanity.com/paper/1910.06508/) (2019) - [Controllable Mixed-Initiative Dialogue Generation through Prompting](https://mlsanity.com/paper/2305.04147/) (2023) - [Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions](https://mlsanity.com/paper/2402.06509/) (2024) - [Planning Like Human: A Dual-process Framework for Dialogue Planning](https://mlsanity.com/paper/2406.05374/) (2024) - [UserRL: Training Interactive User-Centric Agent via Reinforcement Learning](https://mlsanity.com/paper/2509.19736/) (2025) - [Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video](https://mlsanity.com/paper/2510.14560/) (2025) ## Built on by (most cited first, 2 of 2) - [Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents](https://mlsanity.com/paper/2609.37236/) (2026) - [Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym](https://mlsanity.com/paper/2609.37267/) (2026) ## Abstract (arXiv) Large language model agents can plan, invoke tools, and modify external states, yet most systems still take an explicit user instruction as a fixed starting point. Proactive service moves the decision upstream: an agent must infer service opportunities from incomplete environmental and user signals, choose among remaining silent, asking, assisting, and acting, and account for interruption, misunderstanding, overreach, and privacy costs. This survey gives an operational definition centered on initiative and formulates the problem as a partially observable sequential decision process constrained by authorization and risk. The formulation represents timing, content, and delivery within one structured action, while making explicit the option value of waiting, the decision value of questions, and feedback-induced state changes. On this basis, we organize existing methods along one decision pipeline (state and need estimation, intervention gating, action construction, and feedback adaptation) and describe prescribed, predictive, model based, and return optimizing mechanisms as nonexclusive policy-construction components. We further normalize decision units and three-axis evidence descriptors across streaming dialogue, screen, video, software-engineering, and human-agent collaboration resources, and formalize metrics for triggering, timing, calibration, user burden, safety, and policy value. The synthesis shows why offline classification performance alone does not predict deployment benefit and why long-term memory is not a defining condition of proactivity. Reliable proactive service instead requires calibrated incremental intervention value, verifiable authorization, recoverable execution, and counterfactual evidence.