Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning

• URL: http://arxiv.org/abs/2602.09972v1
• Date: Tue, 10 Feb 2026 17:00:16 GMT
• Title: Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
• Abstract summary: We introduce Hydra-Nav, a unified VLM architecture that switches between a deliberative slow system for analyzing exploration history and formulating high-level plans.<n>Experiments demonstrate that Hydra-Nav achieves state-of-the-art performance on the HM3D, MP3D, and OVON benchmarks, outperforming the second-best methods by 11.1%, 17.4%, and 21.2%, respectively.
• Score: 27.764007225331454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large vision-language models (VLMs) show promise for object goal navigation, current methods still struggle with low success rates and inefficient localization of unseen objects--failures primarily attributed to weak temporal-spatial reasoning. Meanwhile, recent attempts to inject reasoning into VLM-based agents improve success rates but incur substantial computational overhead. To address both the ineffectiveness and inefficiency of existing approaches, we introduce Hydra-Nav, a unified VLM architecture that adaptively switches between a deliberative slow system for analyzing exploration history and formulating high-level plans, and a reactive fast system for efficient execution. We train Hydra-Nav through a three-stage curriculum: (i) spatial-action alignment to strengthen trajectory planning, (ii) memory-reasoning integration to enhance temporal-spatial reasoning over long-horizon exploration, and (iii) iterative rejection fine-tuning to enable selective reasoning at critical decision points. Extensive experiments demonstrate that Hydra-Nav achieves state-of-the-art performance on the HM3D, MP3D, and OVON benchmarks, outperforming the second-best methods by 11.1%, 17.4%, and 21.2%, respectively. Furthermore, we introduce SOT (Success weighted by Operation Time), a new metric to measure search efficiency across VLMs with varying reasoning intensity. Results show that adaptive reasoning significantly enhances search efficiency over fixed-frequency baselines.

Related papers

• VerNav: Verifier-First Low-Latency Vision-and-Language Navigation [7.190348268664948]
  Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments according to natural-latency instructions.<n>We propose VerNav, a verifier-first framework for low-language LLM-based VLN.
  arXiv  Detail & Related papers  (2026-09-01T08:45:15Z)
• Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation [68.02899606570223]
  We propose TAMP-Nav, a unified framework for efficient embodied navigation.<n>First, we introduce a Pixel-to-3D Action Formulation (Point) that reformulates navigation into 2D visual coordinates.<n>Second, we propose an integrated Selective Reasoning and Anchor-Trajectory Memory mechanism (Think and Memorize)
  arXiv  Detail & Related papers  (2026-08-18T08:37:08Z)
• EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation [0.0]
  To locate a target object while exploring the unknown environment is a fundamental capability for autonomous agents.<n>In Nav, successful arrival at the target object provides a basic measure of performance.<n>In unknown environments, the key to efficient navigation lies in deciding where to explore next.
  arXiv  Detail & Related papers  (2026-06-17T03:04:11Z)
• DecoVLN: Decoupling Observation, Reasoning, and Correction for Vision-and-Language Navigation [49.233063630722334]
  We propose DecoVLN, a framework for robust streaming perception and closed-loop control in long-horizon navigation.<n>We introduce adaptive refinement mechanism that selects frames from a historical candidate pool by iteratively optimizing a unified scoring function.<n>We also introduce a state-action pair-level corrective finetuning strategy to alleviate compounding errors.
  arXiv  Detail & Related papers  (2026-03-13T16:24:37Z)
• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization [73.98141357780032]
  VLN-CE task requires agents to navigate 3D environments using natural language instructions, without any scene-specific training.<n>Existing methods often fail to achieve robust navigation due to a lack of structured decision-making and insufficient integration of feedback from previous actions.<n>We propose STRIDER, a novel framework that systematically optimize the agent's decision space by integrating spatial layout priors and dynamic task feedback.<n>Our approach introduces two key innovations: 1) a Structured Waypoint Generator that constrains the action space through spatial structure, and 2) a Task-Alignment Regulator that adjusts behavior based on task progress, ensuring semantic alignment throughout navigation.
  arXiv  Detail & Related papers  (2025-10-27T04:37:21Z)
• FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models [75.28505955393591]
  Lane segment reasoning provides comprehensive bird's-eye view (BEV) road scene understanding.<n>Stream-based temporal propagation method has demonstrated promising results by incorporating temporal cues at both the query and BEV levels.<n>We propose FASTopoWM, a novel fast-slow lane segment reasoning framework augmented with latent world models.
  arXiv  Detail & Related papers  (2025-07-31T08:12:56Z)
• DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation [55.888688171010365]
  DORAEMON is a cognitive-inspired framework consisting of Ventral and Dorsal Streams that mimics human navigation capabilities.<n>We evaluate DORAEMON on the HM3D, MP3D and GOAT datasets, where it achieves state-of-the-art performance on both success rate (SR) and success weighted by path length (SPL) metrics.
  arXiv  Detail & Related papers  (2025-05-28T04:46:13Z)
• MPVO: Motion-Prior based Visual Odometry for PointGoal Navigation [3.9974562667271507]
  Visual odometry (VO) is essential for enabling accurate point-goal navigation of embodied agents in indoor environments. Recent deep-learned VO methods show robust performance but suffer from sample inefficiency during training. We propose a robust and sample-efficient VO pipeline based on motion priors available while an agent is navigating an environment.
  arXiv  Detail & Related papers  (2024-11-07T15:36:49Z)
• Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation [72.24964965882783]
  Reinforcement learning (RL) is a promising approach for robotic navigation, allowing robots to learn through trial and error.<n>Real-world robotic tasks often suffer from sparse rewards, leading to inefficient exploration and suboptimal policies.<n>We introduce Confidence-Controlled Exploration (CCE), a novel method that improves sample efficiency in RL-based robotic navigation without modifying the reward function.
  arXiv  Detail & Related papers  (2023-06-09T18:45:15Z)

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.