研究库 论文知识库

内容库 / 论文

arXiv:2609.15195 · 评测基准

HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

类型：arxiv
标识：2609.15195
链接：https://arxiv.org/abs/2609.15195
主分类：evaluation
形态：method
TLDR：Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actions to follow instructions or locate objects. Training-based methods face generalization challenges, while training-free methods exploit multimodal large language models (MLLMs) but often lack mechanisms to reconcile proposed actions with spatial evidence, task progress, and execution failures. We present HarnessVLN, a zero-shot, training-free framework whose Agent Harness coordinates perception, retrieval, grounding, navigation, recovery, and termination through a unified tool i
副分类：engineering
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-16-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

文档 Stephen 自测 · R69 · 2026-09-08

笔记 Tom 文献雷达 · Agent + RAG + Long Context · 2026-08-01 14:40 CST

仓库 jlucasmcrell/ComfyUI-H3-Multishot

笔记 Tom 文献雷达 · Agent / RAG / 长上下文 · 2026-08-29 08:40

笔记 Tom 文献雷达 · Agent RAG LongContext · 2026-08-12 20:40

笔记 Tom 文献雷达 · AI Agent / RAG / 长上下文 · 2026-08-20

arXiv

2609.15195

TLDR

Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actions to follow instructions or locate objects. Training-based methods face generalization challenges, while training-free methods exploit multimodal large language models (MLLMs) but often lack mechanisms to reconcile proposed actions with spatial evidence, task progress, and execution failures. We present HarnessVLN, a zero-shot, training-free framework whose Agent Harness coordinates perception, retrieval, grounding, navigation, recovery, and termination through a unified tool i

arXiv ↗ 中文全文