While recent advances in reasoning models have demonstrated cognitive behaviors through reinforcement learning, existing approaches struggle to invoke deep reasoning capabilities in multi-turn agents with long-horizon interactions. We propose DeepMiner, a novel framework that elicits such abilities by introducing high-difficulty training tasks and dynamic context window. DeepMiner presents a reverse construction method to generate complex but verifiable question-answer pairs from authentic web sources, which ensures the challenge and reliability of training data while injecting cognitive capabilities into multi-turn reasoning scenarios. We further design an elegant yet effective dynamic context management strategy for both training and inference, utilizing sliding window mechanisms while eliminating the dependency on external summarization models, thereby efficiently empowering the model to handle continuously expanding long-horizon contexts. Through reinforcement learning on Qwen3-32B, we develop DeepMiner-32B, which achieves substantial performance improvements across multiple search agent benchmarks. DeepMiner attains 33.5% accuracy on BrowseComp-en, surpassing the previous best open-source agent by almost 20 percentage points, and demonstrates consistent improvements on BrowseComp-zh, XBench-DeepSearch, and GAIA. Notably, our dynamic context management enables sustained interactions of nearly 100 turns within standard 32k context length, effectively addressing the context limitations that constrain existing multi-turn interaction systems.

This paper introduces a framework for relation extraction (RE) that enhances both accuracy and explainability. The framework has two key components: (i) a reasoning mechanism that formulates relation extraction as a series of text-processing steps inspired by cognitive science, and (ii) an optimization process driven by reinforcement learning (RL) with a novel reward function designed to improve both task accuracy and explanation quality. We call our approach CogRE. Our framework addresses the lack of supervision for language-based explanations in traditional RE by promoting outputs that include important relation keywords. These keywords are drawn from a high-quality dictionary that is automatically constructed using an LLM. We evaluate our approach for the task of one-shot RE using two LLMs and two RE datasets. Our experiments show that CogRE improves explanation quality by addressing two common failure patterns in one-shot RE: poor attention focus and limited one-shot learning capability. For example, our cognitive-structured reasoning with Qwen2.5-15B-Instruct on One-shot NYT29 achieves 24.65% F1, surpassing prior reasoning-based designs. Optimizing this approach with RL using our reward further improves performance by +23.46% (absolute). Finally, human evaluation shows that our best model generates relational keywords closely aligned with gold labels, increasing human explanation quality ratings by 54% (relative).

A deadly drone attack in an impoverished area of Haiti's capital, Port-au-Prince, which killed at least 11 people, including eight children, is being blamed on the government, as the country's use of the UAVs in its war on gangs comes under increasing scrutiny. The incident happened on Saturday night in Cite Soleil, one of Port-au-Prince's most dangerous neighbourhoods, in the city's west along the coast, as Albert Steevenson, known as Djouma or "King Jouma", who is a suspected gang leader, was celebrating his birthday. One of the group's leaders and most notorious figures, Jimmy Cherizier, known as Barbecue, promised to avenge the attack. Claudia Bobrun, 30, whose daughter was killed in the attack, showed The Associated Press news agency a video of the eight-year-old in a pool of blood, as she burst into tears. Merika, another four-year-old victim of the attack, was playing with other children at 8pm in the Simon Pele neighbourhood, in Cite Soleil, where the suspected kamikaze drone exploded.

Haiti police raid gang leader's stronghold in capital 3 hours agoShareSaveLeonardo RochaBBC World Service Americas regional editor Jaroslav LukivBBC NewsShareSaveReutersGang control in Port-au-Prince has led to an almost complete breakdown of law and order The government of Haiti says police have launched a large-scale operation in a shantytown controlled by powerful gang leader Jimmy Chérizier, who is widely known as Barbecue. The authorities say several gang members have been killed in the Lower Delmas area of the capital Port-au-Prince. Local reports say military drones carrying explosives are being used in the operation. He said it was the work of a special task force created two days ago to tackle insecurity.Reuters Jimmy'Barbecue' Chérizier has become one of the most powerful gang leaders in Haiti Chérizier, aged 47, is the feared leader of Viv Ansam (Live Together), a coalition of gangs that control much of the city. It is not clear whether Kenyan police officers deployed in Haiti last year to help fight the gangs are involved in the security operation.

Previous research on multimodal entity linking (MEL) has primarily employed contrastive learning as the primary objective. However, using the rest of the batch as negative samples without careful consideration, these studies risk leveraging easy features and potentially overlook essential details that make entities unique. In this work, we propose JD-CCL (Jaccard Distance-based Conditional Contrastive Learning), a novel approach designed to enhance the ability to match multimodal entity linking models. JD-CCL leverages meta-information to select negative samples with similar attributes, making the linking task more challenging and robust. Additionally, to address the limitations caused by the variations within the visual modality among mentions and entities, we introduce a novel method, CVaCPT (Contextual Visual-aid Controllable Patch Transform). It enhances visual representations by incorporating multi-view synthetic images and contextual textual representations to scale and shift patch representations. Experimental results on benchmark MEL datasets demonstrate the strong effectiveness of our approach.

Differential Privacy (DP) can be applied to raw text by exploiting the spatial arrangement of words in an embedding space. We investigate the implications of such text privatization on Language Models (LMs) and their tendency towards stereotypical associations. Since previous studies documented that linguistic proficiency correlates with stereotypical bias, one could assume that techniques for text privatization, which are known to degrade language modeling capabilities, would cancel out undesirable biases. By testing BERT models trained on texts containing biased statements primed with varying degrees of privacy, our study reveals that while stereotypical bias generally diminishes when privacy is tightened, text privatization does not uniformly equate to diminishing bias across all social domains. This highlights the need for careful diagnosis of bias in LMs that undergo text privatization.

Large Language Models (LLMs) have made remarkable strides in various tasks. Whether LLMs are competitive few-shot solvers for information extraction (IE) tasks, however, remains an open problem. In this work, we aim to provide a thorough answer to this question. Through extensive experiments on nine datasets across four IE tasks, we demonstrate that current advanced LLMs consistently exhibit inferior performance, higher latency, and increased budget requirements compared to fine-tuned SLMs under most settings. Therefore, we conclude that LLMs are not effective few-shot information extractors in general. Nonetheless, we illustrate that with appropriate prompting strategies, LLMs can effectively complement SLMs and tackle challenging samples that SLMs struggle with. And moreover, we propose an adaptive filter-then-rerank paradigm to combine the strengths of LLMs and SLMs. In this paradigm, SLMs serve as filters and LLMs serve as rerankers. By prompting LLMs to rerank a small portion of difficult samples identified by SLMs, our preliminary system consistently achieves promising improvements (2.4% F1-gain on average) on various IE tasks, with an acceptable time and cost investment.

Geospatial sciences include a wide range of applications, from environmental monitoring transportation to infrastructure planning, as well as location-based analysis and services. Graph theory algorithms in mathematics have emerged as indispensable tools in these domains due to their capability to model and analyse spatial relationships efficiently. This article explores the applications of graph theory algorithms in geospatial sciences, highlighting their role in network analysis, spatial connectivity, geographic information systems, and various other spatial problem-solving scenarios like digital twin. The article provides a comprehensive idea about graph theory's key concepts and algorithms that assist the geospatial modelling processes and insights into real-world geospatial challenges and opportunities. It lists the extensive research, innovative technologies and methodologies implemented in this domain. Keywords: Graph theory, Geospatial Science, Digital twin 1. Introduction Geospatial science has developed as a vibrant field characterised by intellectual vigour, conceptual expansion, and improved analytical skills as a consequence of the Quantitative Revolution in the subject of geography through a spatially integrated socio-environmental science that outshines prior disciplinary ties, borders, and limitations (Berry et al., 2008). Geospatial science, commonly referred to as geomatics (Aina 2012), is a multidisciplinary discipline that focuses on comprehending, analysing, and visualising spatial data about the Earth's surface using information technology to describe the connections between geography, individuals, places, and Earth processes. Technologies like Global Positioning System (GPS), Geographic Information Systems (GIS), and remote sensing are frequently used as observational, measuring, and analytical tools, helping in the understanding of numerous events by providing the information with a spatial context. Geospatial technology is being used increasingly in every industry today, including resource management, disaster management, forestry, logistics, infrastructure planning, and the study of climate change and other environmental issues (Dangermond and Goodchild, 2020). Geospatial technology and the information created are becoming increasingly significant in all economic sectors, making the economy, society, and the environment an indispensable pillar of sustainable development. (Scott and Rajabifard, 2017).

South Dakota Sen. Mike Rounds shares key takeaways from senators' closed meeting with tech titans like Elon Musk and Mark Zuckerberg on their concerns about artificial intelligence and the need for regulation. Spain has established Europe's first artificial intelligence (AI) policy task force, taking a decisive first step in determining laws around the promising but controversial technology as many governments remain uncertain about the best way forward. The Council of Ministers on Aug. 22 approved a Royal Decree to create the Spanish Agency for the Supervision of Artificial Intelligence (AESIA), a task force that will work under the guidance of the Ministry of Economic Affairs and Digital Transformation. The task force is the first of its kind in Europe, following on from the European Union's Artificial Intelligence Act, which sought to try and establish a framework for governance and oversight of the growing technology. The decree cited the "unquestionable" global impact of AI technology and the rapid advancement the technology has undergone.

Hall of Fame tennis coach Rick Macci weighs in on how fans will react to a computer commentator instead of a human one on'Fox & Friends.' The United Nations Security Council is holding its first-ever meeting on the potential risks artificial intelligence poses to the maintenance of international peace and security. Organized by the United Kingdom, U.K. Ambassador Barbara Woodward announced the July 18 gathering on Monday. The talks will include remarks from experts in the emergent field, as well as input from U.N. Secretary-General Antonio Guterres. Last month, he warned that alarm bells over the most advanced form of AI are "deafening."