# PlannerForge：面向自动驾驶运动规划器的LLM智能体场景测试框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-08 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.news/items/cmtvf0he702x1ronbif6fjym4
- 原文链接：https://arxiv.org/abs/2609.08965

## AI 摘要

PlannerForge 是一个 LLM 智能体框架，覆盖从场景生成到 ADS 评估的全部场景测试阶段，并新增 ADS 增强与 ADS 基准测试两个环节。在 10 个现成 LLM、5 种提示条件下，各任务最佳得分为 0.88-1.00，开源 20-35B 后端在多数任务上追平商业 API。

## 正文

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation, retrieval, modification, ADS execution, and results analysis are performed by separate tools with little interaction. Large Language Model (LLM) agents have shown promise across ADS sub-systems such as perception, planning, and control. However, no prior work covers the whole scenario-based testing pipeline for ADSs with a unified LLM-agent framework. We present PlannerForge, an LLM-agent framework that extends all scenario-based testing stages (from Scenario Generation to ADS Assessment) and adds two further LLM-enhanced stages: ADS Enhancement and ADS Benchmarking. We evaluate PlannerForge with 10 off-the-shelf LLMs across all tasks (Generation, Selection, Modification, Module Routing, Planner Testing, and Enhancement) under 5 prompt conditions. Best-per-task scores range from 0.88 to 1.00, and open-source 20-35B backends match commercial APIs on most tasks. Open-source models such as Qwen3.6:35B match commercial APIs on three of the five tasks. Chaining the modules end-to-end retains 83% / 78% of seed queries (commercial / open). It outperforms Scenario Factory 2.0 (Finkeldei et al., 2025) on natural-language generation (193 vs. 144 executable of 200) and realises 92-96% of requested city, road and vehicle attributes. It outperforms BM25 (Robertson and Zaragoza, 2009) at rank 1 selection (92.0% vs. 67.5%) and From-Words-to-Collisions (Gao et al., 2025) on physically valid edits (>=94% vs. 31%). At N=400, cost-tuning lifts planner success from 50.4% to 70.2% and cuts collisions from 19.0% to 8.4%, without domain-specific fine-tuning.