With the emergence of large language models (LLMs), LLM-powered multi-agent systems (LLM-MA systems) have been proposed to tackle real-world tasks. However, their agents mostly follow predefined Standard Operating Procedures (SOPs) that remain unchanged across the whole interaction, lacking autonomy and scalability. Additionally, current solutions often overlook the necessity for effective agent cooperation. To address the above limitations, we propose MegaAgent, a practical framework designed for autonomous cooperation in large-scale LLM Agent systems. MegaAgent leverages the autonomy of agents to dynamically generate agents based on task requirements, incorporating features such as automatically dividing tasks, systematic planning and monitoring of agent activities, and managing concurrent operations. In addition, MegaAgent is designed with a hierarchical structure and employs system-level parallelism to enhance performance and boost communication. We demonstrate the effectiveness of MegaAgent through Gobang game development, showing that it outperforms popular LLM-MA systems; and national policy simulation, demonstrating its high autonomy and potential to rapidly scale up to 590 agents while ensuring effective cooperation among them. Our results indicate that MegaAgent is the first autonomous large-scale LLM-MA system with no pre-defined SOPs, high effectiveness and scalability, paving the way for further research in this field. Our code is at https://anonymous.4open.science/r/MegaAgent-81F3.

To assist human fact-checkers, researchers have developed automated approaches for visual misinformation detection. These methods assign veracity scores by identifying inconsistencies between the image and its caption, or by detecting forgeries in the image. However, they neglect a crucial point of the human fact-checking process: identifying the original meta-context of the image. By explaining what is actually true about the image, fact-checkers can better detect misinformation, focus their efforts on check-worthy visual content, engage in counter-messaging before misinformation spreads widely, and make their explanation more convincing. Here, we fill this gap by introducing the task of automated image contextualization. We create 5Pils, a dataset of 1,676 fact-checked images with question-answer pairs about their original meta-context. Annotations are based on the 5 Pillars fact-checking framework. We implement a first baseline that grounds the image in its original meta-context using the content of the image and textual evidence retrieved from the open web. Our experiments show promising results while highlighting several open challenges in retrieval and reasoning. We make our code and data publicly available.

Most existing Question Answering Datasets (QuADs) primarily focus on factoid-based short-context Question Answering (QA) in high-resource languages. However, the scope of such datasets for low-resource languages remains limited, with only a few works centered on factoid-based QuADs and none on non-factoid QuADs. Therefore, this work presents MuNfQuAD, a multilingual QuAD with non-factoid questions. It utilizes interrogative sub-headings from BBC news articles as questions and the corresponding paragraphs as silver answers. The dataset comprises over 370K QA pairs across 38 languages, encompassing several low-resource languages, and stands as the largest multilingual QA dataset to date. Based on the manual annotations of 790 QA-pairs from MuNfQuAD (golden set), we observe that 98\% of questions can be answered using their corresponding silver answer. Our fine-tuned Answer Paragraph Selection (APS) model outperforms the baselines. The APS model attained an accuracy of 80\% and 72\%, as well as a macro F1 of 72\% and 66\%, on the MuNfQuAD testset and the golden set, respectively. Furthermore, the APS model effectively generalizes certain a language within the golden set, even after being fine-tuned on silver labels.

Former FBI Special Agent Nicole Parker joins'Cavuto Live' to weigh in on the cancellation of the Taylor Swift concerts in Vienna due to a terror plot. Former President Trump promoted images on Sunday, including some generated through artificial intelligence, showing apparent support from singer Taylor Swift and her fans, triggering a widespread media outcry. Trump posted a collage of Swift-related images to his Truth Social account showing apparent support from the pop star and her diehard fans known as "Swifties." One doctored image played off the classic Uncle Sam recruiting posters, showing Swift in red, white and blue with the caption, "Taylor Swift Wants You To Vote For Donald Trump." Over the images, he wrote, "I accept!"

Born on 16 June 1965, Mr Lynch is the son of a nurse and a fireman, and was raised near Chelmsford in Essex. He studied Natural Sciences at the University of Cambridge, where he earned a PhD in mathematical computing, and later undertook a research fellowship. In 1991, Mr Lynch helped establish Cambridge Neurodynamics - a firm which specialised in using computer-based detection and recognition of fingerprints. His tech firm Autonomy was created five years later, using a statistical method known as "Bayesian inference" at the core of its software. The company's fast-paced growth and success throughout the late 1990s and early 2000s saw Mr Lynch earn a number of awards and accolades.

Former president Donald Trump has shared AI-generated images that falsely claim Taylor Swift fans are supporting his campaign. In a post on Truth Social, Trump shared screenshots of four posts on X that purport to show a number of young women all wearing "Swifties for Trump" T-shirts in a variety of styles. One of the screenshots claimed that Swifties are supporting Trump now after Taylor Swift canceled her concert in Vienna due to security concerns. Another image included the phrase "Taylor wants you to vote for Donald Trump." "I accept!" Trump captioned his post. However, Trump's post appears to contain a mixture of real and AI-generated images that falsely suggest a widespread and coordinated movement of Swifties for Trump.

It has become conventional wisdom among the halls of the United States government that China will launch a full-scale invasion of Taiwan within the next few years. And when that happens, the US military has a relatively straightforward response in mind: Unleash hell. Speaking to The Washington Post on the sidelines of the International Institute for Strategic Studies' annual Shangri-La Dialogue in June, US Indo-Pacific Command chief Navy Admiral Samuel Paparo colorfully described the US military's contingency plan for a Chinese invasion of Taiwan as flooding the narrow Taiwan Strait between the two countries with swarms of thousands upon thousands of drones, by land, sea, and air, to delay a Chinese attack enough for the US and its allies to muster additional military assets in the region. "I want to turn the Taiwan Strait into an unmanned hellscape using a number of classified capabilities," Paparo said, "so that I can make their lives utterly miserable for a month, which buys me the time for the rest of everything." Cheap, easily weaponizable drones have transformed battlefields from Ukraine to the Middle East in recent years, and the US military is rapidly adapting to this new uncrewed future.

Ukrainian President Volodymyr Zelenskyy for the first time stated the aim of Ukraine's August 6 incursion into Russia's Kursk region, saying the operation was necessary to create a buffer zone. Ukrainian Air Force commander Mykola Oleshchuk said the air force destroyed a second strategically important bridge over the Seym River in the Kursk region. He posted an aerial video of a blast tearing through the bridge, which appeared to be near the village of Zvannoye, about 15km (nine miles) north of the Ukrainian border. Vasily Golubev, the governor of Russia's southern Rostov region, said falling debris from a Ukrainian drone attack triggered a large fire at an oil storage facility in the town of Proletarsk. There were no reports of injuries.

Imbalanced datasets are a significant challenge in real-world scenarios. They lead to models that underperform on underrepresented classes, which is a critical issue in infrastructure inspection. This paper introduces the Enhanced Feature Pyramid Network (E-FPN), a deep learning model for the semantic segmentation of culverts and sewer pipes within imbalanced datasets. The E-FPN incorporates architectural innovations like sparsely connected blocks and depth-wise separable convolutions to improve feature extraction and handle object variations. To address dataset imbalance, the model employs strategies like class decomposition and data augmentation. Experimental results on the culvert-sewer defects dataset and a benchmark aerial semantic segmentation drone dataset show that the E-FPN outperforms state-of-the-art methods, achieving an average Intersection over Union (IoU) improvement of 13.8% and 27.2%, respectively. Additionally, class decomposition and data augmentation together boost the model's performance by approximately 6.9% IoU. The proposed E-FPN presents a promising solution for enhancing object segmentation in challenging, multi-class real-world datasets, with potential applications extending beyond culvert-sewer defect detection.

By integrating external knowledge, Retrieval-Augmented Generation (RAG) has become an effective strategy for mitigating the hallucination problems that large language models (LLMs) encounter when dealing with knowledge-intensive tasks. However, in the process of integrating external non-parametric supporting evidence with internal parametric knowledge, inevitable knowledge conflicts may arise, leading to confusion in the model's responses. To enhance the knowledge selection of LLMs in various contexts, some research has focused on refining their behavior patterns through instruction-tuning. Nonetheless, due to the absence of explicit negative signals and comparative objectives, models fine-tuned in this manner may still exhibit undesirable behaviors such as contextual ignorance and contextual overinclusion. To this end, we propose a Knowledge-aware Preference Optimization strategy, dubbed KnowPO, aimed at achieving adaptive knowledge selection based on contextual relevance in real retrieval scenarios. Concretely, we proposed a general paradigm for constructing knowledge conflict datasets, which comprehensively cover various error types and learn how to avoid these negative signals through preference optimization methods. Simultaneously, we proposed a rewriting strategy and data ratio optimization strategy to address preference imbalances. Experimental results show that KnowPO outperforms previous methods for handling knowledge conflicts by over 37\%, while also exhibiting robust generalization across various out-of-distribution datasets.