DialFRED

How to read this picture

ALFRED extension where the agent may ask a human questions about locations, appearance, or direction to finish tasks.1

Sources
Last checked 10 Oct 2026Basic entry15 of 21 facts checked at the sourceNext check 8 Apr 2027
Runs in
Simulation2
Checked against real robots
Not checked
Skill
Working with people
Robot
Game character3
Used by
1104
citations
Licence
Unclear5

Comparisons with real robots

No comparison found Unknown

Details

No real-robot evaluation in the paper or repo; none found in a web search.

Details

About

What it is
Benchmark Inferred1
More

Classified by the Atlas from how the authors describe and distribute it.

Built by
UCLA (Xiaofeng Gao, Ran Gong); Amazon Alexa AI (Qiaozi Gao, Kaixiang Lin, Govind Thattai, Gaurav Sukhatme); USC (Sukhatme). Work supported by Amazon Alexa AI.3
Released
2022-02 (arXiv v1 2022-02-27)1
Version
arXiv v2 (2022-08-15)1
Last update
EvalAI DialFRED Challenge 2022-10-01 to 2023-06-30 (phase 'CVPR 2023 EAI Workshop'); repo last commit 2023-09-146
More

Commit date via GitHub API.

Status
Dormant Inferred7
More

Challenge closed 2023-06; last commit 2023-09.

Setup

Runs in
Simulation2
Robot
Game character3
Setting
Whole home3
Size
53K human QA pairs for 29,376 sub-goals; 25 sub-goal types; 3 question types; 112 rooms; 80 object types; ~$10K annotation cost3

Scoring and access

Scored by
Success rate, Path efficiency3
Leaderboard
Official leaderboard2
Code licence
Creative Commons Attribution-NonCommercial 4.0 International (repo LICENSE file); THIRD_PARTY folder carries ALFRED's MIT licence5
More

GitHub API reports NOASSERTION because CC BY-NC is not a recognised code licence.

Data licence
CC BY-NC 4.0 (human QA CSV ships inside the repo under the repo LICENSE) Inferred5
More

Data file ./data/dialfred_human_qa.csv is in the same repo; no separate data licence found.

Sources 7

  1. 1DialFRED: Dialogue-Enabled Agents for Embodied Instruction FollowingPaper · Feb 2022 · checked 10 Oct 2026
  2. 2EvalAI: Evaluating state of the art in AILeaderboard · checked 10 Oct 2026
  3. 3DialFRED: Dialogue-Enabled Agents for Embodied Instruction FollowingPaper · Feb 2022 · checked 10 Oct 2026
  4. 4Semantic Scholar API recordIndex · checked 10 Oct 2026
  5. 5xfgao/DialFRED on GitHub (blob)Repository · checked 10 Oct 2026
  6. 6https://eval.ai/api/challenges/challenge/1859/Leaderboard · checked 10 Oct 2026
  7. 7xfgao/DialFRED on GitHub (repository)Repository · checked 10 Oct 2026

Change history

  1. Created as a basic entry: identity facts checked at primary sources (phase 1 re-verification).