# PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation

arXiv: https://arxiv.org/abs/2601.09926 · HTML: https://mlsanity.com/paper/2601.09926/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Large Language Models Empowered Personalized Web Agents](https://mlsanity.com/paper/2410.17236/) (2024)
- [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://mlsanity.com/paper/2406.12639/) (2024)
- [Towards Human-centered Proactive Conversational Agents](https://mlsanity.com/paper/2404.12670/) (2024)
- [MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation](https://mlsanity.com/paper/2010.07497/) (2020)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [Proactive Conversational Agents with Inner Thoughts](https://mlsanity.com/paper/2501.00383/) (2024)
- [Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations](https://mlsanity.com/paper/2402.15062/) (2024)
- [Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty](https://mlsanity.com/paper/2412.06771/) (2024)
- [STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents](https://mlsanity.com/paper/2405.12059/) (2024)
- [ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences](https://mlsanity.com/paper/2206.05291/) (2022)
- [Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer](https://mlsanity.com/paper/2201.06095/) (2022)
- [Proactive Recommendation with Iterative Preference Guidance](https://mlsanity.com/paper/2403.07571/) (2024)
- [Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process](https://mlsanity.com/paper/2402.19350/) (2024)
- [Efficient and Responsible Adaptation of Large Language Models for Robust Top-k Recommendations](https://mlsanity.com/paper/2405.00824/) (2024)
- [YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks](https://mlsanity.com/paper/2501.09355/) (2025)
- [Tapestry of Time and Actions: Modeling Human Activity Sequences using Temporal Point Process Flows](https://mlsanity.com/paper/2307.10305/) (2023)

## Built on by (most cited first, 2 of 2)

- [ProactBench: Beyond What The User Asked For](https://mlsanity.com/paper/2605.09228/) (2026)
- [TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration](https://mlsanity.com/paper/2606.04743/) (2026)

## Abstract (arXiv)

Current approaches to proactive assistance move beyond the ask-and-respond paradigm by anticipating user needs. In practice, they either burden users with clarifying questions or rely on context-based extrapolation, often leading to unnecessary or mistimed interventions. Such systems lack explicit mechanisms to model users' knowledge gaps, resulting in incomplete or suboptimal task outcomes. To address this, we propose PROPER, a framework that explicitly models user-specific knowledge gaps in a controlled manner. Central to our approach is the notion of dimensions: structured, task-relevant factors that define the considerations required for effective task completion. Given a user query, the DGA (Dimension Generating Agent) identifies explicit dimensions (from the user's query) and generates a set of candidate implicit dimensions capturing unarticulated aspects of the task. The RGA (Response Generating Agent) integrates both explicit and implicit dimensions selectively to produce personalized, context-aware, and proactively informative responses. We evaluate PROPER across multiple domains using a structured, gap-aware rubric that measures coverage, initiative appropriateness, and intent alignment. PROPER improves on quality scores and win rates across all domains, achieving up to 84% gains in single-turn evaluation and consistent dominance in multi-turn interactions. All code for PROPER is available at: https://github.com/i-kiran/ProPer-Agent.