# ReferClaw: Disambiguating User Intent for Egocentric Assistance

**Authors:** Hangyu Qin, Junbin Xiao, Angela Yao  
**Published:** 5 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.07683) · [PDF](https://arxiv.org/pdf/2611.07683) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.07683.html)

## Abstract

Users of egocentric AI assistants often ask short, ambiguous questions whose intended referents cannot be uniquely resolved from video and dialogue history. For example, "Where did I leave it?" may refer to several previously handled objects. Existing VideoQA systems typically commit to a single interpretation, risking plausible but intention-misaligned answers. We introduce ReferClaw, an agentic framework that formulates egocentric streaming QA as an interactive process: the assistant asks clarifying questions to resolve user intent before answering. Three cooperating agents identify candidate interpretations, request clarification, and generate answers grounded in the resolved intent and visual evidence. A bounded, cost-aware policy balances expected information gain against user effort while limiting clarification turns and question complexity. Referclaw learns from interaction through intent-specific skill updates and process-reward-guided policy optimization with agent-level credit assignment. Evaluations on augmented egocentric QA benchmarks demonstrate improved answer accuracy and joint answer-and-grounding performance over existing baselines, alongside zero-shot transfer across datasets. These findings support interactive clarification as a practical approach to resolving online user intent in egocentric streaming assistance.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.