AI Paper Atlas

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

Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles

Jiawei Liu, Xun Gong, Fen Fang, Muli Yang, Bohao Qu, Yunfeng Hu, Hong Chen, Xulei Yang, Qing Guo

CVPR 2026 · Large language models › Agents, code and math · approach: LLM-driven embodied and driving agents · 0 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
replace multi-query LLM decision (DiLu++) with a single-query LLM-generated planner scheduling scriptLLM+MPC instruction realization · POINT benchmarkInstruction Realization: 0.51 -> 0.84Improved
use explicit MPC planners with LLM scheduling instead of diffusion-based test-time optimization (Diffusion-ES)instruction-realization methods · POINT benchmarkInstruction Realization: 0.28 -> 0.84Improved
add traffic context to the LLM input (ablation)Intent inference with DeepSeekV3 · POINT benchmarkIntent Recognition: 0.78 -> 0.86Improved
add LLM planner scheduling over a single fixed planner (ablation)MPC planner suite · POINT benchmarkInstruction Realization: 0.17 -> 0.84 (vs Lane Keeping PL)Improved
add LLM planner scheduling over a single acceleration planner (ablation)MPC planner suite · POINT benchmarkCollision avoidance: 0.57 -> 0.99Improved
scale up LLM size for intent recognition (ablation)Intent inference · POINT benchmarkIntent RecognitionImproved
add reasoning mechanisms and larger context windows to the LLM (ablation)Intent inference · POINT benchmarkIntent RecognitionImproved
increase LLM inference latency from 0 to 4 seconds (ablation)scheduling framework · POINT benchmarkInstruction Realization (REA): 0.84 -> 0.39Hurt
increase LLM inference latency from 0 to 4 seconds (ablation)scheduling framework · POINT benchmarkCollision avoidance: 0.99 -> 0.98No clear effect
add a specialized-AD comparison: ours versus PDM-Closed on expert progressscheduling framework · POINT benchmarkExpert trajectory progress: 0.92 -> 0.82Hurt

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