DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation

• URL: http://arxiv.org/abs/2604.12486v1
• Date: Tue, 14 Apr 2026 09:11:55 GMT
• Title: DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation
• Abstract summary: Long-horizon collaborative vision-language navigation (VLN) is critical for multi-robot systems to accomplish complex tasks beyond the capability of a single agent.<n>We present Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation (DeCoNav)<n>DeCoNav is a decentralized framework that couples event-triggered dialogue with dynamic task allocation and replanning for real-time, adaptive coordination.
• Score: 51.978605314711835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon collaborative vision-language navigation (VLN) is critical for multi-robot systems to accomplish complex tasks beyond the capability of a single agent. CoNavBench takes a first step by introducing the first collaborative long-horizon VLN benchmark with relay-style multi-robot tasks, a collaboration taxonomy, along with graph-grounded generation and evaluation to model handoffs and rendezvous in shared environments. However, existing benchmarks and evaluations often do not enforce strictly synchronized dual-robot rollout on a shared world timeline, and they typically rely on static coordination policies that cannot adapt when new cross-agent evidence emerges. We present Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation (DeCoNav), a decentralized framework that couples event-triggered dialogue with dynamic task allocation and replanning for real-time, adaptive coordination. In DeCoNav, robots exchange compact semantic states via dialogue without a central controller. When informative events such as new evidence, uncertainty, or conflicts arise, dialogue is triggered to dynamically reassign subgoals and replan under synchronized execution. Implemented in DeCoNavBench with 1,213 tasks across 176 HM3D scenes, DeCoNav improves the both-success rate (BSR) by 69.2%, demonstrating the effectiveness of dialogue-driven, dynamically reallocated planning for multi-robot collaboration.

Related papers

• HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration [62.19372189311434]
  We introduce HRIBench, a diagnostic benchmark for intent-aware human-robot collaboration based on executable scenarios.<n>HRIBench represents collaborative tasks as structured scenario scripts that explicitly model agent roles, temporal dependencies, coordination constraints, and human behavior distributions.<n>Results show that current foundation robot policies struggle substantially in collaborative settings despite strong manipulation ability.
  arXiv  Detail & Related papers  (2026-07-05T09:15:35Z)
• Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs [52.26652574704317]
  Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes.<n>We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems.
  arXiv  Detail & Related papers  (2026-05-07T14:19:17Z)
• Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation [54.6417539730783]
  Question-Asking Navigation (QAsk-Nav) is the first reproducible benchmark for Collaborative Instance Object Navigation (CoIN)<n>We develop Light-CoNav, a lightweight unified model for collaborative navigation that is 3x smaller and 70x faster than existing modular methods.
  arXiv  Detail & Related papers  (2026-03-31T21:45:00Z)
• EmCoop: A Framework and Benchmark for Embodied Cooperation Among LLM Agents [18.802912315746564]
  EmCoop is a benchmark framework for studying cooperation in embodied multi-agent systems.<n>Our framework separates a high-level cognitive layer from a low-level embodied interaction layer.<n>We propose generalizable, process-level metrics that diagnose collaboration quality and failure modes.
  arXiv  Detail & Related papers  (2026-02-27T22:28:33Z)
• VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs [51.18508300818979]
  Vision Language-Language Navigation (VL-LN) benchmark provides a large-scale, automatically generated dataset for training and assessing dialog-enabled navigation models.<n>VL-LN comprises over 41k long-horizon dialog-augmented trajectories for training and an automatic evaluation protocol with an oracle capable of responding to agent queries.
  arXiv  Detail & Related papers  (2025-12-26T19:00:12Z)
• Advancing Audio-Visual Navigation Through Multi-Agent Collaboration in 3D Environments [37.73614419658084]
  MASTAVN is a scalable framework enabling two agents to collaboratively localize and navigate toward an audio target in shared 3D environments.<n>MASTAVN achieves significant reductions in task completion time and notable improvements in navigation success rates compared to single-agent and non-collaborative baselines.
  arXiv  Detail & Related papers  (2025-09-21T05:05:26Z)
• SayCoNav: Utilizing Large Language Models for Adaptive Collaboration in Decentralized Multi-Robot Navigation [10.877873071364148]
  We present SayCoNav, a new approach that leverages large language models (LLMs) for automatically generating this collaboration strategy among a team of robots.<n>We evaluate SayCoNav on Multi-Object Navigation (MultiON) tasks, that require the team of the robots to utilize their complementary strengths to efficiently search multiple different objects in unknown environments.
  arXiv  Detail & Related papers  (2025-05-19T20:58:06Z)
• CAMON: Cooperative Agents for Multi-Object Navigation with LLM-based Conversations [22.79813240034754]
  Large language models (LLMs) have exhibited remarkable comprehension and planning abilities. This paper proposes a framework for decentralized multi-agent navigation, leveraging LLM-enabled communication and collaboration.
  arXiv  Detail & Related papers  (2024-06-30T09:14:33Z)
• Unified Human-Scene Interaction via Prompted Chain-of-Contacts [61.87652569413429]
  Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. This paper presents a unified HSI framework, UniHSI, which supports unified control of diverse interactions through language commands.
  arXiv  Detail & Related papers  (2023-09-14T17:59:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.