AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving

Enhui Ma, Lijun Zhou, Tao Tang, Jiahuan Zhang, Junpeng Jiang, Zhan Zhang, Dong Han, Kun Zhan, Xueyang Zhang, Xianpeng Lang, Haiyang Sun, Xia Zhou and 2 more

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DriveSora generated data (without PM-Agent) to random duplication (ablation)CorrectAD on UniAD · nuScenes valavg collision rate (%): 0.35 -> 0.31Improved
add PM-Agent to tailor data to failure cases (without DriveSora) (ablation)CorrectAD on UniAD · nuScenes valavg collision rate (%): 0.35 -> 0.29Improved
combine PM-Agent and DriveSora (ablation)CorrectAD on UniAD · nuScenes valavg L2: 1.09 -> 0.98Improved
use multi-round inquiry (classify then analyze) instead of one-step VLM prompt (ablation)PM-Agent · Failure cause analysissemantic distance: 4.72 -> 3.49Improved
use DriveSora instead of Panacea as video generator (ablation)CorrectAD on UniAD · nuScenes valavg collision rate (%): 0.27 -> 0.19Improved
increase CorrectAD iterations from 1 to 3 (ablation)CorrectAD on UniAD · nuScenes valavg L2: 1.06 -> 0.98Improved
increase CorrectAD iterations from 1 to 3 (ablation)CorrectAD on UniAD · nuScenes valHellinger distance to failure distribution: 0.15 -> 0.09Improved
add multimodal prompt (layout and caption conditions) to DriveSora (ablation)DriveSora · nuScenes valNDS: 25.23 -> 36.37Improved
add multi-view spatial attention to DriveSora (ablation)DriveSora · nuScenes valCLIP: 79.5 -> 86.73Improved
add unconditional background nullification to CFG (CFG Text,Fore,Back vs Text,Fore) (ablation)DriveSora CFG · nuScenes valFVD / Map mIoU: FVD 89.12 -> 94.60; mIoU 34.40 -> 35.96Mixed
use multi-condition CFG instead of MagicDrive CFG (ablation)DriveSora · nuScenes valFVD: 164.48 -> 94.60Mixed
generate data with CorrectAD instead of retrieving data with AIDEUniAD · nuScenes valavg collision rate (%): 0.28 -> 0.19Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy