AI Paper Atlas

Research map / Large language models / Agents, code and math

Making Large Language Models Better Planners with Reasoning-Decision Alignment

Zhijian Huang, Tao Tang, Shaoxiang Chen, Sihao Lin, Zequn Jie, Lin Ma, Guangrun Wang, Xiaodan Liang

ECCV 2024 · Large language models › Agents, code and math · approach: LLM-driven embodied and driving agents · 26 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 reasoning-decision alignment loss (ablation)RDA-Driver · DriveLM-nuScenes CoT scoreCoT score: 62 -> 71Improved
add ranking and binary alignment losses together (ablation)RDA-Driver · nuScenes val (UniAD metrics)L2 avg (m): 0.85 -> 0.80Improved
add ranking and binary alignment losses together (ablation)RDA-Driver · nuScenes val (UniAD metrics)Collision avg (%): 0.44 -> 0.32Improved
add binary loss only (without ranking) (ablation)RDA-Driver · nuScenes val (UniAD metrics)L2 avg (m): 0.85 -> 0.87No clear effect
use BEV features flattened by region instead of CLIP encoder (ablation)RDA-Driver · nuScenes val (UniAD metrics)Collision avg (%): 0.48 -> 0.41Improved
replace BEV flattening with BEV pooling (ablation)RDA-Driver · nuScenes val (UniAD metrics)L2 avg (m): 0.84 -> 1.35Hurt
use multi-turn CoT instead of single-turn with all CoT types (ablation)RDA-Driver · nuScenes val (UniAD metrics)L2 avg (m): 0.90 -> 0.80Improved
add perception, prediction and decision CoTs to single-turn QA (ablation)RDA-Driver · nuScenes val (UniAD metrics)L2 avg (m): 1.01 -> 0.90Improved
drop any one of perception, prediction, decision CoT from multi-turn setup (ablation)RDA-Driver · nuScenes val (UniAD metrics)L2 avg (m): 0.80 -> 0.87 to 0.91Hurt
evaluate on DriveLM-nuScenes instead of nuScenes to reduce ego-status leakageUniAD · UniAD metricsL2 avg (m): 1.03 -> 3.00Hurt
RDA-Driver versus VAD on ST-P3 L2RDA-Driver · nuScenes val (ST-P3 metrics)L2 avg (m): 0.37 -> 0.40No clear effect

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