Goto

Collaborating Authors

 national council


MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning

arXiv.org Artificial Intelligence

We present MA-RAG, a Multi-Agent framework for Retrieval-Augmented Generation (RAG) that addresses the inherent ambiguities and reasoning challenges in complex information-seeking tasks. Unlike conventional RAG methods that rely on end-to-end fine-tuning or isolated component enhancements, MA-RAG orchestrates a collaborative set of specialized AI agents: Planner, Step Definer, Extractor, and QA Agents, each responsible for a distinct stage of the RAG pipeline. By decomposing tasks into subtasks such as query disambiguation, evidence extraction, and answer synthesis, and enabling agents to communicate intermediate reasoning via chain-of-thought prompting, MA-RAG progressively refines retrieval and synthesis while maintaining modular interpretability. Extensive experiments on multi-hop and ambiguous QA benchmarks, including NQ, HotpotQA, 2WikimQA, and TriviaQA, demonstrate that MA-RAG significantly outperforms standalone LLMs and existing RAG methods across all model scales. Notably, even a small LLaMA3-8B model equipped with MA-RAG surpasses larger standalone LLMs, while larger variants (LLaMA3-70B and GPT-4o-mini) set new state-of-the-art results on challenging multi-hop datasets. Ablation studies reveal that both the planner and extractor agents are critical for multi-hop reasoning, and that high-capacity models are especially important for the QA agent to synthesize answers effectively. Beyond general-domain QA, MA-RAG generalizes to specialized domains such as medical QA, achieving competitive performance against domain-specific models without any domain-specific fine-tuning. Our results highlight the effectiveness of collaborative, modular reasoning in retrieval-augmented systems: MA-RAG not only improves answer accuracy and robustness but also provides interpretable intermediate reasoning steps, establishing a new paradigm for efficient and reliable multi-agent RAG.


Top secret Iranian drone site used by IRGC, terror proxies exposed by opposition group

FOX News

IDF Special Operations veteran Aaron Cohen and executive director of The Lawfare Project Brooke Goldstein react to Israel's'limited' retaliatory strike on Iran on'Hannity.' The People's Mojahedin Organization of Iran (MEK), an exiled Iranian resistance group, provided a report to Fox News Digital presenting evidence of a top-secret unmanned aerial vehicle (UAV) site in the Islamic Republic of Iran, north of Qom City in the Ganjine region. According to the report, members of the Islamic Revolutionary Guard Corps (IRGC) are trained to use "all kinds of drones" at the base, including the Mohajer series, manufactured by Qods Aviation Industry. Employees of Qods Aviation Industry also reportedly use the site to train small groups of Iranian proxy operatives of Hezbollah, as well as members of Iranian proxy groups from Syria, Yemen and Iraq, to use the Mohajer-4 drone platform. The National Council of Resistance of Iran (NCRI), based on information from the MEK, told Fox News Digital that the site is a proving ground for Mohajer-4, Mohajer-6, and Mohajer-10 drones.


Can AI Chatbots Pass the Fundamentals of Engineering (FE) and Principles and Practice of Engineering (PE) Structural Exams?

arXiv.org Artificial Intelligence

The engineering community has recently witnessed the emergence of chatbot technology with the release of OpenAI ChatGPT-4 and Google Bard. While these chatbots have been reported to perform well and even pass various standardized tests, including medical and law exams, this forum paper explores whether these chatbots can also pass the Fundamentals of Engineering (FE) and Principles and Practice of Engineering (PE) exams. A diverse range of civil and environmental engineering questions and scenarios are used to evaluate the chatbots' performance, as commonly present in the FE and PE exams. The chatbots' responses were analyzed based on their relevance, accuracy, and clarity and then compared against the recommendations of the National Council of Examiners for Engineering and Surveying (NCEES). Our report shows that ChatGPT-4 and Bard, respectively scored 70.9% and 39.2% in the FE exam and 46.2% and 41% in the PE exam. It is evident that the current version of ChatGPT-4 could potentially pass the FE exam. While future editions are much more likely to pass both exams, this study also highlights the potential of using chatbots as teaching assistants and guiding engineers.


Iran sent more than 3,500 drones to Russia for its war against Ukraine: intel dossier

FOX News

Fox News national security correspondent Jennifer Griffin provides insight on responding to drone attacks in Ukraine on "America Reports." The Paris-based dissident organization National Council of Resistance of Iran (NCRI) accused the Iranian regime of furnishing Russian strongman Vladimir Putin's army with more than 3,500 drones for his scorched-earth war against Ukraine. According to reports from the social network of the People's Mojahedin Organization of Iran (PMOI/MEK) inside the Islamic Republic, "Iran's UAV [unmanned aerial vehicle] sale contract to Russia includes various offensive drones, including Shahed-129, Mohajer-6 and suicide drones Shahed-136 and Shahed-131." MEK is part of the National Council of Resistance of Iran umbrella organization. The NCRI dossier states, "Tehran has sold more than 3,500 UAVs to Russia. Most of these were made at the factories of the Ministry of Defense, with others produced by the factories of the Iranian Aviation and Space Industries Association (IASIA)."


Survey of the use of Artificial Intelligence in Brazilian Judiciary

#artificialintelligence

The Center for Innovation, Administration and Research in the Judiciary (CIAPJ) of the Getulio Vargas Foundation (FGV) released the report of the first phase of the research "Technology applied to conflict resolution in the Brazilian Judiciary " (click here to obtain the PDF document) carried out in December 2020. This research was coordinated by the Minister of the Superior Court of Justice (STJ) Luis Felipe Salomรฃo. The research covered 3 of the 5 branchs of the Brazilian Judiciary: State Justice, Labor Justice, Federal Justice, Electoral Justice and Military Justice. The collection of these data was carried out with 59 (fifty-nine) courts (Federal Supreme Court -- STF, Superior Court of Justice -- STJ, Superior Labor Court -- TST, Regional Labor Courts, Federal Regional Courts and Courts of Justice) and the National Council of Justice. The report indicates that half of the courts have an artificial intelligence project under development or already implemented.


Iran dissidents warn of regime's use of drones to 'destabilize' region, using materials from China

FOX News

Iranian dissidents are warning of the hard-line regime's use of drones to cause instability in the region, saying it is using the technology โ€“ materials for which are being imported from China โ€“ to make up for the weaknesses of its air force. The National Council of Resistance of Iran (NCRI), an umbrella group of Iranian resistance groups that oppose the regime, released evidence in a press conference it says shows the production and utilization of unmanned aerial vehicles (UACs) for terrorist operations and for assisting its proxies in the Middle East โ€“ including aerial photographs of the alleged sites and details that have emerged from inside the country. "Our revelation today is significant because it shows that the Qods Force of the IRGC has in recent years expanded its arsenal to step up terrorism and warmongering to destabilize the region by arming its proxies with UAVs," Alireza Jafarzadeh, deputy director of the Washington office of the National Council of Resistance of Iran, told Fox News. "This is in line with the regime's nuclear defiance and its repression at home." The group alleges that the regime, which has been rocked by a slew of economic sanctions imposed by the Trump administration as well as protests at home and challenges related to its handling of the COVID-19 pandemic, has used a web of industries to spend billions of dollars to produce components or smuggle them in from foreign countries.


Artificial Intelligence For Studying Ancient Human Populations Of Patagonia

#artificialintelligence

Argentine and Spanish researchers have used statistical techniques of automatic learning to analyze mobility patterns and technology of the hunter-gatherer groups that inhabited the Southern Cone of America, from the time they arrived about 12,000 years ago until the end of the 19th century. Big data from archaeological sites located in the extreme south of Patagonia have been used for this study. The presence of humans on the American continent dates back to at least 14,500 years ago, according to datings made at archaeological sites such as Monte Verde, in Chile's Los Lagos Region. But the first settlers continued moving towards the southernmost confines of America. Now, researchers from Argentina's National Council for Scientific and Technical Research (CONICET) and two Spanish institutions (the Spanish National Research Council and the University of Burgos) have analyzed the relationships between mobility and technology developed by those societies that originated in the far south of Patagonia.