日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

VLAarXiv:2504.04040

ADAPT: あらゆるタスクの選好を能動的に発見・適応する手法

ADAPT: Actively Discovering and Adapting to Preferences for any Task

シェア:XThreadsFacebookLINEはてブBluesky

ユーザーの選好を能動的な質問で引き出しながら家事タスクを遂行するベンチマークADAPTと、そのためのLLM訓練手法Reflection-DPOを提案。

著者: Maithili Patel, Xavier Puig, Ruta Desai, Roozbeh Mottaghi, Sonia Chernova, Joanne Truong, Akshara Rai

分類: cs.AI, cs.RO

原文アブストラクト

Assistive agents should be able to perform under-specified long-horizon tasks while respecting user preferences. We introduce Actively Discovering and Adapting to Preferences for any Task (ADAPT) -- a benchmark designed to evaluate agents' ability to adhere to user preferences across various household tasks through active questioning. Next, we propose Reflection-DPO, a novel training approach for adapting large language models (LLMs) to the task of active questioning. Reflection-DPO finetunes a 'student' LLM to follow the actions of a privileged 'teacher' LLM, and optionally ask a question to gather necessary information to better predict the teacher action. We find that prior approaches that use state-of-the-art LLMs fail to sufficiently follow user preferences in ADAPT due to insufficient questioning and poor adherence to elicited preferences. In contrast, Reflection-DPO achieves a higher rate of satisfying user preferences, outperforming a zero-shot chain-of-thought baseline by 6.1% on unseen users.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  3. 3newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI