Fertiliser source can influence crop growth and soil properties, but comparative information for pea cultivation under the mid-hill agro-climatic conditions of Himachal Pradesh remains limited. A field experiment was conducted at Panjiala Village, Kangra District, Himachal Pradesh, India, during the rabi season from December 2025 to March 2026 to evaluate the effects of organic and inorganic fertilisers on soil health and the growth performance of pea (Pisum sativum L.) cv. PB-89. The experiment was laid out in a randomised block design (RBD) with three treatments and three replications: T₁ (vermicompost applied at 5 t ha⁻¹, equivalent to 3.0 kg per gross plot), T₂ (seaweed-fortified granules applied at 416.7 kg ha⁻¹, equivalent to 250 g per gross plot), and T₃ (unfertilised control). The fertilisers were thoroughly incorporated into the soil before sowing, and observations were recorded from the net plot area (2.4 m × 1.8 m). Soil samples collected before sowing and after harvest were analysed for pH, electrical conductivity (EC), organic carbon, available phosphorus, potassium, sulphur, calcium, magnesium, soil texture, and soil colour. Plant height and number of leaves were recorded at weekly intervals from December to March. The organic treatment produced the greatest plant height (76.0 ± 8.25 cm) and number of leaves (79.0 ± 8.40) and increased soil organic carbon from 0.80% before sowing to 1.10% after harvest. In contrast, the inorganic treatment recorded the highest available phosphorus (32.8 kg ha⁻¹) and potassium (385.6 kg ha⁻¹) after harvest. Soil pH remained slightly to moderately acidic, while EC remained within the normal range under all treatments. These results suggest that vermicompost was more effective in improving vegetative growth and soil organic carbon, whereas seaweed-fortified granules enhanced the availability of phosphorus and potassium under the agro-climatic conditions of Himachal Pradesh.
Arti Rana, Simran, Madhu et al.· International Journal of Pla...· 0 citations
The rapid expansion of capabilities in Large Language Model (LLM) agents has exposed a critical architectural bottleneck: when agents are given access to a flat, monolithic registry of tools, the model must evaluate hundreds or thousands of options simultaneously. This leads to decision-space explosion, context window saturation, and degraded routing accuracy. To address these limitations, this paper presents a hierarchical, skill-based architecture for agentic orchestration. Capabilities are organized as a rooted tree where internal nodes make routing decisions and leaf nodes execute deterministic tasks. The runtime enforces a single-step execution loop governed by a Last-In-First-Out (LIFO) stack, giving the agent a form of memory akin to a Pushdown Automaton, therefore enabling it to track nested execution contexts and resume deterministically from any depth. Capability discovery follows a manifest-driven, lazy-loading protocol: only the immediate children of the active node are loaded, so memory and prompt costs scale with the explored path rather than the global registry. By replacing global memory with localized stack frames, the architecture prevents outputs from one execution branch from leaking into another, establishing the isolation guarantees required for deployment in regulated enterprise environments. We also discuss UPI Help, an AI-powered digital payments support product, as a motivating production deployment context. We provide a mathematical formalization of the orchestration state, detailed algorithmic analysis of the execution loop, and controlled benchmarks comparing flat and hierarchical routing under increasing tool catalogs, multi-step workflow pressure, and visible schema-token exposure per LLM call.
Prashant Devadiga, Abhishek, Adithya Mishra et al.· 0 citations
Rising global temperatures have altered the frequency, intensity and spatial distribution of extreme weather events, with direct and measurable consequences for agricultural productivity worldwide. This review synthesises evidence on how heatwaves, drought, flooding, tropical cyclones and their compound or sequential combinations affect the yield of major cereal and grain legume crops, with particular attention to wheat, maize, rice and soybean. Physiological mechanisms underlying yield loss are examined alongside field- and satellite-derived evidence of production shortfalls, and the modulating role of elevated atmospheric carbon dioxide concentration is considered. The review further evaluates adaptation strategies, including climate-smart agriculture, breeding for abiotic stress tolerance and agronomic management, and identifies the growing recognition that compound extremes, rather than single hazards, now pose the greatest threat to global food security. Evidence indicates that yield penalties associated with extreme heat, water deficit and excess soil moisture are often non-linear and interact with crop developmental stage, soil condition and regional climate. The review concludes that closing gaps in compound-event attribution, regionally disaggregated yield data and the integration of adaptation research across disciplines remains essential for safeguarding future food production under a changing climate.
Basharat Bashir, L. Ahmad, S. Qayoom et al.· International Journal of Env...· 0 citations