Ranjan Sapkota

There is great interest in alternative pollination strategies for crop production in the face of climate change and perennial threats to the traditional pollination mechanisms. This review explores the potential of robotic pollination as a promising solution to these challenges affecting crop fertilization, agricultural sustainability, and global food production. We comprehensively examine recent advances in robotic pollination systems that integrate artificial intelligence, machine vision, robotics, and precision sensing to supplement or complement conventional insect‐mediated pollination. The review first examines aerial robotic pollination, beginning with insect‐scale aerial robots, their technological evolution from biomimetic flapping‐wing platforms toward autonomous operation, and the key challenges that continue to limit their practical deployment. It then reviews unmanned aerial vehicles (UAVs) for robotic pollination, highlighting their progression from broad aerial pollen dispersal to precision‐oriented pollination, followed by a synthesis of current limitations and future research priorities for UAV‐based robotic pollination. The review subsequently discusses ground‐based robotic pollination systems, emphasizing their perception, navigation, and pollen delivery strategies together with the technical challenges associated with field deployment. Beyond individual robotic platforms, we examine the cost, scalability, and commercial development of robotic pollination technologies and discuss emerging industrial efforts that are accelerating adoption in modern agriculture. Finally, we present a future roadmap for robotic crop pollination, outlining critical research directions in autonomy, perception, precision pollen delivery, multirobot coordination, ecological compatibility, and system‐level intelligence required to transition robotic pollination from experimental prototypes to commercially viable agricultural solutions. Overall, this review highlights robotic pollination as a practical, intelligent, and environmentally sustainable technology for modern agriculture, capable of enhancing crop pollination resilience, mitigating pollinator decline and labor shortages, and supporting long‐term agricultural productivity and global food security.

This survey presents a first comprehensive analysis of the emerging paradigm of Agentic Agriculture, tracing the evolution from model-centric artificial intelligence to integrated, goal-driven agentic systems in precision agriculture. It begins with clearly defined research objectives and a structured literature synthesis methodology. The review covers foundational AI agents for core tasks, including sensing and monitoring, decision-support and advisory systems, and robotic field operations such as harvesting, spraying, and crop monitoring. Building on these, the survey examines multi-agent systems enabling distributed farm intelligence through IoT-agent architectures, swarm robotics, and multi-agent reinforcement learning for coordinated farm management and operational optimization. It then advances to Agentic AI, where autonomous agents extend these systems by integrating perception, reasoning, planning, and action into unified workflows. Applications include adaptive irrigation, crop monitoring, and resource allocation, supported by digital twins that evolve from static simulations to closed-loop, decision-driven optimization platforms. The survey further explores autonomous agricultural ecosystems with human-AI collaboration and coordinated robotics, including reinforcement learning-based irrigation and multi-robot harvesting. Finally, it identifies challenges in reliability, safety, data governance, ethics, and regulation. Overall, Agentic AI enables scalable, adaptive, and knowledge-driven agricultural systems, requiring robust integration of data-driven and process-based models for trustworthy deployment.

Modern Artificial Intelligence (AI) increasingly relies on multi-agent architectures that blend visual and language understanding. Yet, a pressing challenge remains: How can we trust these agents especially in zero-shot settings with no fine-tuning? We introduce a novel modular Agentic AI visual classification framework that integrates generalist multimodal agents with a non-visual reasoning orchestrator and a Retrieval-Augmented Generation (RAG) module. Applied to apple leaf disease diagnosis, we benchmark three configurations: (I) zero-shot with confidence-based orchestration, (II) fine-tuned agents with improved performance, and (III) trust-calibrated orchestration enhanced by CLIP-based image retrieval and re-evaluation loops. Using confidence calibration metrics (ECE, OCR, CCC), the orchestrator modulates trust across agents. Our results demonstrate a 77.94% accuracy improvement in the zero-shot setting using trust-aware orchestration and RAG, achieving 85.63% overall. GPT-4o showed better calibration, while Qwen-2.5-VL displayed overconfidence. Furthermore, image-RAG grounded predictions with visually similar cases, enabling correction of agent overconfidence via iterative re-evaluation. The proposed system separates perception (vision agents) from meta-reasoning (orchestrator), enabling scalable and interpretable multi-agent AI. This blueprint illustrates how Agentic AI can deliver trustworthy, modular, and transparent reasoning, and is extensible to diagnostics, biology, and other trust-critical domains. In doing so, we highlight Agentic AI not just as an architecture but as a paradigm for building reliable multi-agent intelligence. All models, prompts, results, and system components including the complete software source code are openly released to support reproducibility, transparency, and community benchmarking at our Github page.

The rapid transition from reactive large language model (LLM) interfaces to persistent, action-capable systems has revealed fundamental gaps in the architectural understanding of Agentic AI, particularly in disentangling inference, orchestration, and execution layers. Despite significant progress, there remains a lack of unified frameworks that systematically explain how autonomous agents can be designed, deployed, and evaluated as full-stack systems. This paper presents a comprehensive, layered analysis of Agentic AI architectures. We begin by establishing the foundations of Agentic AI and layered architectures, examining the evolution from reactive LLMs to persistent agentic systems and identifying core design principles such as modularity, memory hierarchy, and continuous execution. We then analyze OpenClaw and Ollama as a full-stack Agentic AI architecture, where Ollama functions as the LLM inference layer and OpenClaw operates as the agent runtime layer, enabling seamless integration from model inference to autonomous reasoning, planning, and action. To substantiate this architectural perspective, we introduce a prototype experimental validation of the OpenClaw–Ollama fullstack system. Through controlled configurations, benchmark task design, and system-level evaluation metrics, the results demonstrate a consistent monotonic improvement in performance as architectural complexity increases, confirming that autonomous capabilities such as tool use and persistent memory emerge from system integration rather than isolated models. Building on these findings, we further analyze operational challenges, safety, and evaluation, highlighting critical issues in security, privacy, governance, and benchmarking of persistent agentic systems. Finally, we explore future research directions, including scalable multi-agent systems, distributed architectures, and human-centered, responsible autonomous AI. Overall, this work establishes a unified architectural framework for Agentic AI, provides empirical validation of full-stack autonomous systems, and outlines a roadmap toward scalable, secure, and trustworthy autonomous agents. Prototype experimental validation, architecture, models, code, and experimental datasets are openly released to support reproducibility, transparency, and community benchmarking at GitHub.

Information fusion for trustworthy AI is entering a pivotal stage, where Large Language Model (LLM)-based agents excel at integrating multi-source knowledge into coherent reasoning chains. However, these agents remain opaque and difficult to audit in the absence of embedded, in-loop safety mechanisms. Existing surveys treat reasoning, agentic behavior, and safety in isolation, leaving a gap in how to integrate them into practical, trustworthy agents. To address this, we present a survey at the intersection of these domains and introduce Responsible Reasoning AI Agents (R2A2), a class of agentic LLM systems that generate explicit reasoning traces while enforcing fairness, privacy, transparency, accountability, and auditability throughout the decision loop. We synthesize recent advances in chain-of-thought prompting, ReAct, tree/graph-of-thought structures, tool use, memory, retrieval, and agentic browsing, and integrate these with responsible AI principles into a unified evaluation framework. Furthermore, we propose an evaluation methodology for agentic reasoning with embedded safety mechanisms and outline a five-stage reproducible protocol: Curate, Unify, Probe, Benchmark, Analyze, to operationalize responsibility metrics. Overall, this taxonomy, metric suite, and framework advance the development of safe, transparent, and governable LLM-based agents. The project repository is available on GitHub § https://github.com/shainarazavi/Responsible-reasoning-agents.

Given the rapid emergence and applications of Multi-Modal Large Language Models (MM-LLMs) across various scientific fields, insights regarding their applicability in agriculture are still only partially explored. This paper conducts an in-depth review of MM-LLMs in agriculture, focusing on understanding how MM-LLMs can be developed and implemented to optimize agricultural processes, increase efficiency, and reduce costs. Recent studies have explored the capabilities of MM-LLMs in agricultural information processing and decision-making. Despite these advancements, significant gaps persist, particularly in addressing domain-specific challenges such as variable data quality and availability, integration with existing agricultural systems, and the creation of robust training datasets that accurately represent complex agricultural environments. Moreover, a comprehensive understanding of the capabilities, challenges, and limitations of MM-LLMs in agricultural information processing and application is still missing. Exploring these areas is crucial to providing the community with a broader perspective and a clearer understanding of MM-LLMs’ applications, establishing a benchmark for the current state and emerging trends in this field. To bridge this gap, this survey reviews the progress of MM-LLMs and their utilization in agriculture, with an additional focus on 11 key research questions (RQs), where 4 RQs are general and 7 RQs are agriculture focused. By addressing these RQs, this review outlines the current opportunities and challenges, limitations, and future roadmap for MM-LLMs in agriculture. The findings indicate that multi-modal MM-LLMs not only simplify complex agricultural challenges but also significantly enhance decision-making and improve the efficiency of agricultural image processing. These advancements position MM-LLMs as an essential tool for the future of farming. For continued research and understanding, an organized and regularly updated list of papers on MM-LLMs is available at https://github.com/JiajiaLi04/Multi-Modal-LLMs-in-Agriculture.

This paper presents a comparative overview of the LangChain, LangGraph, and LangSmith as toolchains for agentic orchestration, covering architecture, functionality, and end-to-end LLMOps. We introduce a taxonomy that distinguishes chain-based composition, stateful graph orchestration, observability/evaluation layers, and map capabilities to high-impact applications such as retrieval-augmented generation (RAG), multi-agent planning, and human-in-the-loop workflows. We detail conversion patterns (chain-graph) and middleware strategies for interoperability including shared state schemas, event buses, and standardized telemetry to streamline integration. To move beyond anecdote, we propose a reproducible benchmarking protocol measuring throughput, latency, scalability, memory behavior, and a developer-centric metric: debugging resolution time. Case studies demonstrate hybrid stacks that pair LangChain for rapid construction, LangGraph for adaptive orchestration, and LangSmith for continuous monitoring, testing, and governance. Finally, we surface current limits complexity growth, state explosion, and transparency gaps and outline future directions: modular state abstraction, unified observability, ethics-by-design, performance-aware routing, and auto-evaluation pipelines. The result is a practical framework for selecting, composing, and evolving Agentic AI systems from prototype to production, improving reliability, developer experience, and time-to-value. The project page for this study is available at https://rashik.info.np/agentic_ai_toolchains/