Interactive Navigation Beyond Reachability: Benchmark and Agentic Framework

Experiments on MultINav-Bench show that MultINav-Agent consistently outperforms adapted baselines across channel, container, and mixed tasks. It comes from a paper posted to arXiv on 14 October 2026. Existing embodied navigation tasks commonly assume that traversability and object states remain fixed during an episode. Yet reaching a goal may require opening a door to access a room and then opening a container to reveal a hidden target. We formulate interactive navigation beyond reachability, unifying channel-induced changes in spatial connectivity, container-induced changes in target visibility, and their sequential dependencies. We introduce MultINav-Bench, a 3K-episode ObjectGoal benchmark in MolmoSpaces spanning channel, container, and mixed tasks, with interaction-necessity annotations covering required and unnecessary episodes. Its data generation pipeline automates task construction across multiple task types. The evaluation protocol separately measures navigation success, interaction effectiveness, and cost. We further propose MultINav-Agent, a three-stage agentic framework built on a persistent, state-conditioned interaction graph. Semantic interactive perception grounds entities and interaction states; a vision-language model selects task-relevant actions based on expected changes in connectivity and target observability; and post-interaction verification updates the graph to guide subsequent navigation, exploration, or interaction.

Why it counts

Experiments on MultINav-Bench show that MultINav-Agent consistently outperforms adapted baselines across channel, container, and mixed tasks.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.