---
format: "aidr-story-markdown/v1"
id: "843a57ee54b1d50cbc632bc290e1350eb5409fbf266a47ba32efb62609920ffe"
canonical_url: "https://aidr.today/843a57ee?lang=en"
title: "Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-13T00:00:00.000Z"
category: "Research"
topics: ["agent"]
source_urls: ["https://huggingface.co/papers/2609.35965"]
summary: "Researchers present Systematic Multi-Agent Vision-and-Language Navigation as a constrained coordination problem for teams of robots. They introduce the MAVLN benchmark, featuring 11,724 episodes across 145 scenes, and TRISS, a navigation system utilizing an LLM-based scheduler, shared topological memory, and a conflict-aware execution mechanism."
---

# Systematic Multi\-Agent Vision\-and\-Language Navigation: Formulation, Benchmark, and Method

> [Open the canonical story](<https://aidr.today/843a57ee?lang=en>)

**Published:** 2026-10-13T00:00:00.000Z
**Category:** Research
**Topics:** agent

## Summary

Researchers present Systematic Multi\-Agent Vision\-and\-Language Navigation as a constrained coordination problem for teams of robots\. They introduce the MAVLN benchmark, featuring 11,724 episodes across 145 scenes, and TRISS, a navigation system utilizing an LLM\-based scheduler, shared topological memory, and a conflict\-aware execution mechanism\.

## Sources

- [Story source](<https://huggingface.co/papers/2609.35965>)