mlsanityData to 14 Oct 2026

EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation

arXiv 2606.18235 ↗First posted 16 Jun 2026cs.AIcited by 0

On the map: Synthetic data and self-improvement for LLMs → Self-evolving LLM agents

Abstract (arXiv)

Zero-Shot Object-Goal Navigation (ZS-OGN) requires embodied agents to explore and locate target objects without any prior training. To this end, recent methods leverage foundation models. But they typically rely on static priors and lack adaptation, which leads to repeated errors and costly trial and error. In this paper, we propose a self-evolving ZS-OGN framework that enables continuous test-time improvement. Specifically, we build an agentic rule memory by extracting actionable knowledge from past trajectories. Then, we propose a retrieval strategy based on upper confidence bound, selecting effective rules by balancing semantic relevance and historical success. In addition, we introduce a memory-guided preflection module that forecasts potential outcomes before action, reducing inefficient exploration. Extensive experiments show that our method outperforms existing zero-shot baselines, achieving a 10.1% improvement in success rate with fewer unnecessary steps.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Self-evolving LLM agents, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 32 of its 58 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

32 of 58 references.

References · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2024Qwen2.5 Technical Reportcited by 4,942
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  7. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 781
  8. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 362
  9. 2020ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objectscited by 244
  10. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 233
  11. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 205
  12. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
20 more
  1. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
  2. 2023L3MVN: Leveraging Large Language Models for Visual Target Navigationcited by 120
  3. 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 109
  4. 2023PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNavcited by 93
  5. 2024OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Modelscited by 67
  6. 2024Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversationscited by 36
  7. 2026TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMscited by 24
  8. 2022Search for or Navigate to? Dual Adaptive Thinking for Object Navigationcited by 20
  9. 2024Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Modelscited by 19
  10. 2024StraGo: Harnessing Strategic Guidance for Prompt Optimizationcited by 17
  11. 2023Object Goal Navigation with Recursive Implicit Mapscited by 16
  12. 2025VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraftcited by 13
  13. 2025MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigationcited by 13
  14. 2024Multi-Floor Zero-Shot Object Navigation Policycited by 12
  15. 2025Enhancing Jailbreak Attacks on LLMs via Persona Promptscited by 11
  16. 2025Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Explorationcited by 10
  17. 2020Efficient Robotic Object Search via HIEM: Hierarchical Policy Learning with Intrinsic-Extrinsic Modelingcited by 9
  18. 2023Exploitation-Guided Exploration for Semantic Embodied Navigationcited by 9
  19. 2025CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Taskscited by 8
  20. 2025EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrievalcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SemNav: A Model-Based Planner for Zero-Shot Object Goal Navigation Using Vision-Foundation Models
  2. 2026EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation
  3. 2026SkillNav: Score-Level Skill Intervention for Zero-Shot Object Goal Navigation
  4. 2026Hierarchical Fast-Slow ReAct Agent for Zero-Shot Object-Goal Navigation
  5. 2026Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
  6. 2026NavHarness: Adaptive Goals for Agentic Vision-Language Navigation
  7. 2026MarvisNav: Making Memory Visible on Route Choices for Zero-Shot Object Navigation ↗
  8. 2026F2A-ObjectNav: An Adaptive Agentic Architecture for Object-Goal Navigation