---
title: "ReferClaw: Disambiguating User Intent for Egocentric Assistance"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07683v1"
permalink: "https://feed.astralor.com/items/itm_274a5dd72e4803c49fc9d45c"
published: "2026-11-05T09:10:14.000Z"
score: 59
channel: "tech"
tags: ["AI Agent","多模态","ReferClaw","Disambiguating User Intent","Egocentric Assistance Users","For","Where","Users"]
---

# ReferClaw: Disambiguating User Intent for Egocentric Assistance

## 速览

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 prev…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_274a5dd72e4803c49fc9d45c