# VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs

arXiv: https://arxiv.org/abs/2512.22342 · HTML: https://mlsanity.com/paper/2512.22342/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2025.

## Built on by (most cited first, 5 of 5)

- [Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation](https://mlsanity.com/paper/2606.03175/) (2026)
- [Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation](https://mlsanity.com/paper/2607.13653/) (2026)
- [VCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience](https://mlsanity.com/paper/2609.34687/) (2026)
- [AVERT-VLN: Abstention-aware Visual Error Recovery and Training for Vision-and-Language Navigation](https://mlsanity.com/paper/2609.39579/) (2026)
- [GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models](https://mlsanity.com/paper/2610.14541/) (2026)

## Abstract (arXiv)

In most existing embodied navigation tasks, instructions are well-defined and unambiguous, such as instruction following and object searching. Under this idealized setting, agents are required solely to produce effective navigation outputs conditioned on vision and language (VL) inputs. Real-world instructions, however, are often underspecified and require interaction to resolve ambiguity and infer user intent. To bridge this gap, we propose Interactive Instance Goal Navigation (IIGN), which extends Instance Goal Navigation (IGN) by allowing agents to freely consult an oracle in natural language while searching for a specific instance. IIGN requires agents to produce both Language and Navigation (LN) outputs, enabling interaction while moving in the environment. To support this task, we introduce VL-LN Bench, a benchmark with an automated data collection pipeline and over 41k collected long-horizon dialog-augmented trajectories for training, alongside an automatic evaluation protocol paired with a dedicated oracle for answering agent queries. Experiments reveal two core bottlenecks of IIGN: long-horizon exploration and fine-grained grounding of textual information to the correct instance among same-category distractors. Although active dialog partially alleviates these challenges, current models still lag far behind human performance. Further ablations validate the value of the data generated by our pipeline and show that the proposed oracle provides scalable assistance comparable to human support, proving VL-LN Bench as a practical testbed for dialog-enabled embodied navigation.