HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation

• URL: http://arxiv.org/abs/2604.08232v1
• Date: Thu, 09 Apr 2026 13:22:24 GMT
• Title: HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
• Abstract summary: HiRO-Nav is the first kind of agent capable of adaptively determining whether to perform thinking at every step based on its own action entropy.<n>We propose a tailored training pipeline comprising hybrid supervised fine-tuning as a cold start, followed by online reinforcement learning.<n>Experiments on the textscCHORES-$mathbbS$ ObjectNav benchmark showcases that HiRO-Nav achieves a better trade-off between success rates and token efficiency than both dense-thinking and no-thinking baselines.
• Score: 58.29060712443587
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied navigation agents built upon large reasoning models (LRMs) can handle complex, multimodal environmental input and perform grounded reasoning per step to improve sequential decision-making for long-horizon tasks. However, a critical question remains: \textit{how can the reasoning capabilities of LRMs be harnessed intelligently and efficiently for long-horizon navigation tasks?} In simple scenes, agents are expected to act reflexively, while in complex ones they should engage in deliberate reasoning before acting.To achieve this, we introduce \textbf{H}ybr\textbf{i}d \textbf{R}eas\textbf{O}ning \textbf{Nav}igation (\textbf{HiRO-Nav}) agent, the first kind of agent capable of adaptively determining whether to perform thinking at every step based on its own action entropy. Specifically, by examining how the agent's action entropy evolves over the navigation trajectories, we observed that only a small fraction of actions exhibit high entropy, and these actions often steer the agent toward novel scenes or critical objects. Furthermore, studying the relationship between action entropy and task completion (i.e., Q-value) reveals that improving high-entropy actions contributes more positively to task success.Hence, we propose a tailored training pipeline comprising hybrid supervised fine-tuning as a cold start, followed by online reinforcement learning with the proposed hybrid reasoning strategy to explicitly activate reasoning only for high-entropy actions, significantly reducing computational overhead while improving decision quality. Extensive experiments on the \textsc{CHORES}-$\mathbb{S}$ ObjectNav benchmark showcases that HiRO-Nav achieves a better trade-off between success rates and token efficiency than both dense-thinking and no-thinking baselines.

Related papers

• Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning [82.58758211120319]
  We show that different tasks can exhibit exploration-exploitation pace mismatch.<n>This back-and-forth interaction creates inter-task entropy crossovers and frequent entropy spikes.<n>Inspired by this observation, we introduce Entropy Pacing Policy Optimization (EPPO) for multi-task agentic Large Language Model (LLM) tasks.
  arXiv  Detail & Related papers  (2026-07-08T09:13:05Z)
• AIPO: Learning to Reason from Active Interaction [54.10819421625103]
  AIPO enables the policy model to proactively consult three functional collaborative agents when encountering reasoning bottlenecks.<n>AIPO consistently improves reasoning performance, generalizes robustly across different policy models and RLVR algorithms, and effectively expands the reasoning capability boundary of the policy model.
  arXiv  Detail & Related papers  (2026-05-08T19:06:55Z)
• SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents [0.31034395048547575]
  Existing approaches rely on static prompting strategies or handcrafteds to select actions such as code editing, file navigation, and test execution.<n>We propose SWE-Shepherd, a framework that introduces Process Reward Models (PRMs) to provide dense, step-level supervision for repository-level code agents.<n>Experiments on SWE-Bench Verified demonstrate improved interaction efficiency and action quality, while also highlighting challenges in aligning intermediate rewards with final task success.
  arXiv  Detail & Related papers  (2026-04-12T06:51:47Z)
• Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts [22.323342919724492]
  HERA is a hierarchical framework that jointly evolves multi-agent orchestration and role-specific agent prompts.<n> HERA achieves an average improvement of 38.69% over recent baselines.<n>Topological analyses reveal emergent self-organization, where sparse exploration yields compact, high-utility multi-agent networks.
  arXiv  Detail & Related papers  (2026-04-01T13:45:52Z)
• Anticipatory Planning for Multimodal AI Agents [77.62643381558613]
  We introduce TraceR1, a two-stage reinforcement learning framework that explicitly trains anticipatory reasoning.<n>TraceR1 is evaluated across seven benchmarks, covering online computer-use, offline computer-use benchmarks, and multimodal tool-use reasoning tasks.<n>Results show that anticipatory trajectory reasoning is a key principle for building multimodal agents that can reason, plan, and act effectively in complex real-world environments.
  arXiv  Detail & Related papers  (2026-03-17T16:55:11Z)
• RAGNav: A Retrieval-Augmented Topological Reasoning Framework for Multi-Goal Visual-Language Navigation [1.7508558850131373]
  Vision-Language Navigation (VLN) is evolving from single-point pathfinding toward the more challenging Multi-Goal VLN.<n>RAGNav is a framework that bridges the gap between semantic reasoning and physical structure.
  arXiv  Detail & Related papers  (2026-03-04T05:31:33Z)
• AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts [78.33143446024485]
  We introduce textbfAgentLongBench, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles.<n>This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios.
  arXiv  Detail & Related papers  (2026-01-28T16:05:44Z)
• Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning [31.17280303212164]
  We propose textbfSpark (textbfStrategic textbfPolicy-textbfAware explotextbfRation via textbfKey-state dynamic branching)<n>Our key insight is to activate adaptive branching exploration at critical decision points to probe promising trajectories.<n>textscSpark achieves superior success rates with significantly fewer training samples, exhibiting robust generalization even in unseen scenarios.
  arXiv  Detail & Related papers  (2026-01-28T03:15:34Z)
• \ extsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation [50.027425808733994]
  textscNaVIDA is a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution.<n>textscNaVIDA augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions.<n>Experiments show that textscNaVIDA achieves superior navigation performance compared to state-of-the-art methods with fewer parameters.
  arXiv  Detail & Related papers  (2026-01-26T06:16:17Z)
• CoINS: Counterfactual Interactive Navigation via Skill-Aware VLM [13.352875026471445]
  We propose Counterfactual Interactive Navigation via Skill-aware VLM (CoINS)<n>We fine-tune a VLM, named InterNav-VLM, which incorporates skill affordance and concrete constraint parameters into the input context.<n>To execute the generated high-level plans, we develop a comprehensive skill library through reinforcement learning.
  arXiv  Detail & Related papers  (2026-01-07T14:10:46Z)
• ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping [54.37497695483689]
  We propose ARES, a unified framework for adaptive reasoning that dynamically allocates exploration effort based on task difficulty.<n>Our approach is motivated by two key empirical findings: (i) while single-token entropy is noisy, high window-entropy (HWE) tokens can reliably capture reasoning-critical moments.<n>In the Adaptive Cold-Start stage, we curate multimodal and textual data paired with reasoning traces of length proportional to problem difficulty, equipping the model with initial difficulty awareness.<n>In the second stage, we develop Adaptive Entropy Policy Optimization (AEPO), which uses HWE tokens as exploration triggers
  arXiv  Detail & Related papers  (2025-10-09T17:03:28Z)
• Risk-Bounded Multi-Agent Visual Navigation via Dynamic Budget Allocation [3.7347677698423536]
  Traditional planning methods excel at solving long-horizon tasks but rely on predefined distance metrics.<n>We propose RB-CBS, a novel extension to Conflict-Based Search (CBS) that dynamically allocates and adjusts user-specified risk bound.<n>Our improved planner ensures that each agent receives a local risk budget enabling more efficient navigation while still respecting overall safety constraints.
  arXiv  Detail & Related papers  (2025-09-09T21:35:55Z)
• Active Test-time Vision-Language Navigation [60.69722522420299]
  ATENA is a test-time active learning framework that enables a practical human-robot interaction via episodic feedback on uncertain navigation outcomes.<n>In particular, ATENA learns to increase certainty in successful episodes and decrease it in failed ones, improving uncertainty calibration.<n>In addition, we propose a self-active learning strategy that enables an agent to evaluate its navigation outcomes based on confident predictions.
  arXiv  Detail & Related papers  (2025-06-07T02:24:44Z)
• RRO: LLM Agent Optimization Through Rising Reward Trajectories [52.579992804584464]
  Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks.<n>In practice, agents sensitive to the outcome of certain key steps which makes them likely to fail the task.<n>We propose Reward Rising Optimization (RRO) to mitigate this issue.
  arXiv  Detail & Related papers  (2025-05-27T05:27:54Z)
• A Multi-Agent Reinforcement Learning Approach for Cooperative Air-Ground-Human Crowdsensing in Emergency Rescue [22.201769922727077]
  This paper tackles the Heterogeneous Collaborative-Sensing Task Allocation problem for emergency rescue, considering humans, UAVs, and UGVs.<n>We introduce a novel Hard-Cooperative'' policy where UGVs prioritize recharging low-battery UAVs, alongside performing their sensing tasks.<n>We propose HECTA4ER, a novel multi-agent reinforcement learning algorithm built upon a Decentralized Execution architecture.
  arXiv  Detail & Related papers  (2025-05-11T14:49:15Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)

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.