Drought stress at the reproductive-stage is a major constraint limiting rice productivity in rainfed ecosystems. The present study evaluated 450 rice (Oryza sativa L.) genotypes along with 8 checks under normal and reproductive-stage drought stress conditions during kharif 2020 at Bihar Agricultural University, Sabour, India, using an augmented randomised complete block design. Drought stress was imposed by withholding irrigation 25–30 days before flowering. Significant variation was observed among genotypes for all studied traits under both environments, indicating substantial genetic diversity for drought response. Stress conditions caused marked reductions in grain yield and related traits, particularly panicle fertility and filled grains per panicle, due to increased spikelet sterility. Genotypes were initially screened using drought susceptibility index (DSI) and those with a DSI of less than 1 were shortlisted for further analysis. To ensure stringent selection, genotypes were ranked based on DSI values and the lowest 20th percentile was considered as drought-tolerant. Further evaluation based on yield under stress and key reproductive traits identified 26 promising drought-tolerant genotypes. Among these, six genotypes, namely ARC 11245 (IRGC 42651-2), SAITA (IRGC 31618-1), KWANG LU AI 4 (IRGC 28480-2), DM 49 (IRGC 8775-1), CRILLO LA FRIA (IRGC 10793-1) and 77 UPLA (GERVEX 159-C1), exhibited DSI values of zero and showed superior yield stability under stress. Principal component analysis revealed that the first three components explained 79.68 % of the total variation, with grain yield, filled grains, total grains and panicle fertility contributing most to variability under stress. The identified genotypes provide promising genetic resources for future drought-tolerance breeding following multi-environment validation.
The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.
Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson· EUROMICRO Conference on Soft...· 64 citations· ⚡6
The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.
Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al.· arXiv.org· 62 citations· ⚡3
The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.
Zheying Zhang, M. Rayhan, Tomas Herda et al.· International Conference on...· 48 citations· ⚡4
This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.
Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al.· arXiv.org· 44 citations· ⚡2
The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.
Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al.· arXiv.org· 41 citations
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 6, 2026