# IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters

arXiv: https://arxiv.org/abs/2604.18375 · HTML: https://mlsanity.com/paper/2604.18375/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [Aligning LLMs with Individual Preferences via Interaction](https://mlsanity.com/paper/2410.03642/) (2024)
- [CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues](https://mlsanity.com/paper/2404.03820/) (2024)
- [OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion](https://mlsanity.com/paper/2506.06913/) (2025)
- [RosePO: Aligning LLM-based Recommenders with Human Values](https://mlsanity.com/paper/2410.12519/) (2024)
- [From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System](https://mlsanity.com/paper/2508.15811/) (2025)
- [User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems](https://mlsanity.com/paper/2504.05522/) (2025)
- [RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenders](https://mlsanity.com/paper/2508.05289/) (2025)
- [MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment](https://mlsanity.com/paper/2503.01711/) (2025)
- [Proactive Guidance of Multi-Turn Conversation in Industrial Search](https://mlsanity.com/paper/2505.24251/) (2025)

## Built on by (most cited first, 1 of 1)

- [What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems](https://mlsanity.com/paper/2608.07565/) (2026)

## Abstract (arXiv)

Conversational agents, such as ChatGPT and Doubao, have become essential daily assistants for billions of users. To further enhance engagement, these systems are evolving from passive responders to proactive companions. However, existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck. In the conversation initiation stage, users may have a vague need but no explicit query intent, creating a first-message barrier where the conversation holds before it begins. To overcome this, we introduce Conversation Starter Generation: generating personalized starters to guide users into conversation. However, unlike in-conversation stages where immediate context guides the response, initiation must operate in a cold-start moment without explicit user intent. To pioneer in this direction, we present IceBreaker that frames human ice-breaking as a two-step handshake: (i) evoke resonance via Resonance-Aware Interest Distillation from session summaries to capture trigger interests, and (ii) stimulate interaction via Interaction-Oriented Starter Generation, optimized with personalized preference alignment and a self-reinforced loop to maximize engagement. Online A/B tests on one of the world's largest conversational agent products show that IceBreaker improves user active days by +0.184% and click-through rate by +9.425%, and has been deployed in production.