# Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions

arXiv: https://arxiv.org/abs/2408.04168 · HTML: https://mlsanity.com/paper/2408.04168/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 8 Aug 2024.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 31)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [Learning to Navigate in Complex Environments](https://mlsanity.com/paper/1611.03673/) (2016)
- [Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2203.12667/) (2022)
- [Building Generalizable Agents with a Realistic and Rich 3D Environment](https://mlsanity.com/paper/1801.02209/) (2018)
- [Learning to Navigate in Cities Without a Map](https://mlsanity.com/paper/1804.00168/) (2018)
- [Evaluating Cognitive Maps and Planning in Large Language Models with CogEval](https://mlsanity.com/paper/2309.15129/) (2023)
- [Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation](https://mlsanity.com/paper/2303.03480/) (2023)
- [VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View](https://mlsanity.com/paper/2307.06082/) (2023)
- [Vision-Language Navigation: A Survey and Taxonomy](https://mlsanity.com/paper/2108.11544/) (2021)
- [Learning To Follow Directions in Street View](https://mlsanity.com/paper/1903.00401/) (2019)
- [Retouchdown: Adding Touchdown to StreetLearn as a Shareable Resource for Language Grounding Tasks in Street View](https://mlsanity.com/paper/2001.03671/) (2020)
- [Language and Sketching: An LLM-driven Interactive Multimodal Multitask Robot Navigation Framework](https://mlsanity.com/paper/2311.08244/) (2023)

## Built on by (most cited first, 25 of 25)

- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking](https://mlsanity.com/paper/2502.12893/) (2025)
- [Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents](https://mlsanity.com/paper/2411.09523/) (2024)
- [Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions](https://mlsanity.com/paper/2510.25445/) (2025)
- [UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces](https://mlsanity.com/paper/2503.06157/) (2025)
- [OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents](https://mlsanity.com/paper/2410.21286/) (2024)
- [CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space](https://mlsanity.com/paper/2502.12532/) (2025)
- [SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment](https://mlsanity.com/paper/2505.14667/) (2025)
- [ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps](https://mlsanity.com/paper/2505.18675/) (2025)
- [FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents](https://mlsanity.com/paper/2507.21071/) (2025)
- [HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction](https://mlsanity.com/paper/2410.09112/) (2024)
- [HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems](https://mlsanity.com/paper/2505.13516/) (2025)
- [A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science](https://mlsanity.com/paper/2504.09848/) (2025)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [R-TOFU: Unlearning in Large Reasoning Models](https://mlsanity.com/paper/2505.15214/) (2025)
- [Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval](https://mlsanity.com/paper/2411.04006/) (2024)
- [LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences](https://mlsanity.com/paper/2509.12273/) (2025)
- [Where Paths Collide: A Comprehensive Survey of Classic and Learning-Based Multi-Agent Pathfinding](https://mlsanity.com/paper/2505.19219/) (2025)
- [Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System](https://mlsanity.com/paper/2506.19433/) (2025)
- [MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs](https://mlsanity.com/paper/2602.18600/) (2026)
- [CrimeMind: Simulating Urban Crime with Multi-Modal LLM Agents](https://mlsanity.com/paper/2506.05981/) (2025)
- [City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs](https://mlsanity.com/paper/2512.15933/) (2025)
- [AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2607.00052/) (2026)

## Abstract (arXiv)

This paper considers a scenario in city navigation: an AI agent is provided with language descriptions of the goal location with respect to some well-known landmarks; By only observing the scene around, including recognizing landmarks and road network connections, the agent has to make decisions to navigate to the goal location without instructions. This problem is very challenging, because it requires agent to establish self-position and acquire spatial representation of complex urban environment, where landmarks are often invisible. In the absence of navigation instructions, such abilities are vital for the agent to make high-quality decisions in long-range city navigation. With the emergent reasoning ability of large language models (LLMs), a tempting baseline is to prompt LLMs to "react" on each observation and make decisions accordingly. However, this baseline has very poor performance that the agent often repeatedly visits same locations and make short-sighted, inconsistent decisions. To address these issues, this paper introduces a novel agentic workflow featured by its abilities to perceive, reflect and plan. Specifically, we find LLaVA-7B can be fine-tuned to perceive the direction and distance of landmarks with sufficient accuracy for city navigation. Moreover, reflection is achieved through a memory mechanism, where past experiences are stored and can be retrieved with current perception for effective decision argumentation. Planning uses reflection results to produce long-term plans, which can avoid short-sighted decisions in long-range navigation. We show the designed workflow significantly improves navigation ability of the LLM agent compared with the state-of-the-art baselines.