Damning new video shows Alex Pretti running at ICE agents and screaming in their faces before smashing feds' tail light Costco faces lawsuit over beloved $4.99 rotisserie chicken amid claims customers were misled What bread's really doing to your body: ROSAMUND DEAN gave it up for a month and tested her health before and after. From blood pressure, to cholesterol and her weight, the results are truly shocking... Man who Beckhams have gone to war with: Why David and Victoria fear'smiling crocodile' Nelson Peltz is behind Brooklyn's outburst... as ALISON BOSHOFF reveals 14-year legal row that proves his'bully billionaire' reputation Kim Kardashian says Harry and Meghan's team asked for removal of party photos when they'realised it was Remembrance Day' 'I can kill you at any time:' Surgeon's fatal threats to ex-wife before she was found dead with her new partner at home, new documents show Jealous killer's cold last words as he's executed for brutal murders of his ex and her new boyfriend Ilhan Omar accuses Trump of being'obsessed' with her as police identify potential liquid sprayed at her during town hall attack Weekend's monster storm to bring freezing temperatures to MIAMI as cold snap ices over millions of Americans Megyn Kelly blasts Alex Pretti for'stalking, harassing and terrorizing' ICE after video shows him kicking SUV's tail light and spitting at agents Telling detail stitched into Melania's Dior dress that hints at her true ambitions, as the First Lady rings the New York Stock Exchange bell: JANE TIPPETT The Kristi Noem call that left Tom Homan seething. The freeze-out no one saw... and why insiders say his Minneapolis mission is do or die Origins of Egypt's Great Pyramid upended as new clues point to lost civilization from 20,000 years ago Margot Robbie stuns in Elizabeth Taylor's iconic necklace as she is joined by Jacob Elordi at Wuthering Heights premiere in LA Hilarious live gaffe on David Muir's World News Tonight that'triggered behind the scenes meltdown' Alex Pretti spits at ICE agents and smashes federal SUV's tail light in shocking footage taken 11 days before he was shot dead Extraordinary transformation of beloved child star who has'self-canceled' and ditched Hollywood to live off grid in POVERTY as'Catholic extremist' NASA gives a glimpse inside Orion's cramped quarters where four astronauts will live for 10 days as they whizz around the moon - 'the smell would be intolerable!' With the first launch window for Artemis II now just days away, NASA has shared a glimpse inside the cramped quarters of the Orion spacecraft. Four astronauts - Reid Wiseman, Victor Glover, Christina Koch, and Jeremy Hansen - will spend 10 days living inside the capsule as they whizz around the moon.

America's great journey in space is about to face its most consequential moment in half a century. Everyone agrees: It's a complete disaster. I. Artemis, We Have a Problem As you may have heard, NASA plans to send a crew of astronauts around the moon in early 2026, followed by a lunar landing in 2027. Or maybe you haven't heard. When I told one of my daughters about this plan to send people to the moon, she said, after a long silence: "But I thought we already sent a bunch of people there a long time ago." This is a standard response when I quiz people about Artemis, NASA's program to return to the moon, and this time to stay . It's named for Apollo's twin sister and the goddess of the moon and the hunt. The other day, I was in a gaggle with six neighbors, all highly informed professional people--two of them with long careers at the National Science Foundation--and none knew anything about Artemis except one thing: It's a plan to send people to Mars. Artemis is a moon mission. There is no Mars mission NASA has no Mars rocket, no Mars capsule, no Mars mission crew. What it does have is a very troubled moon program. Artemis faces fundamental engineering challenges that have called into question the program's basic architecture. Reconfiguring a mission this important is hard in the best of times, but the agency is being forced to do it during a year of unprecedented internal turmoil. A new administration always means turnover, but NASA has been in an uncontrolled spin every bit as alarming as the one Neil Armstrong famously pulled out of during in 1966. More than a year ago, President-elect Donald Trump nominated a billionaire entrepreneur and Elon Musk ally, Jared Isaacman, to become NASA administrator. It was an unconventional choice, but Isaacman drew support from many quarters in the space community. Then, right before Isaacman was poised for confirmation by the Senate, Trump and Musk had a nasty falling-out, and Trump yanked Isaacman's nomination. Since Inauguration Day, NASA had been run by acting administrator Janet Petro, a veteran agency official, and with Isaacman out, she remained in charge until one day in July when Trump suddenly named Secretary of Transportation Sean Duffy as interim administrator.

We introduce Orion, a visual agent that integrates vision-based reasoning with tool-augmented execution to achieve powerful, precise, multi-step visual intelligence across images, video, and documents. Unlike traditional vision-language models that generate descriptive outputs, Orion orchestrates a suite of specialized computer vision tools, including object detection, keypoint localization, panoptic segmentation, Optical Character Recognition (OCR), and geometric analysis, to execute complex multi-step visual workflows. The system achieves competitive performance across MMMU, MMBench, DocVQA, and MMLongBench while extending monolithic VLM capabilities to production-grade visual intelligence. Through its agentic, tool-augmented approach, Orion enables autonomous visual reasoning that bridges neural perception with symbolic execution, marking the transition from passive visual understanding to active, tool-driven visual intelligence. Try Orion for free at: https://chat.vlm.run Learn more at: https://www.vlm.run/orion

Large Language Models (LLMs) have exhibited strong reasoning capabilities and achieved remarkable performance in mathematical problem-solving tasks. Recently, distilling reasoning ability from long-form Chains-of-Thought (CoTs) has emerged as a promising approach for enhancing Small Language Models (SLMs). Existing studies typically treat SLMs as student models and use long-form CoTs as supervision signals for Supervised Fine-Tuning (SFT) to transfer reasoning ability. However, such long-form CoT teachers are usually unaware of the student model's capacity, which limits the effective utilization of the provided reasoning traces. To overcome this limitation, we propose errOr-aware self-ReflectION (ORION), a framework that refines teacher CoTs through an Error-Aware Reflection process. ORION enables the student model to construct more tailored teacher CoTs by refining teacher CoTs and incorporating its own reasoning errors. Experiments on multiple mathematical reasoning benchmarks demonstrate that ORION consistently improves performance by more than 2% over all baselines. Further analysis reveals that the CoTs constructed by ORION exhibit higher coherence and logical consistency, thereby serving as more effective supervision signals for SFT. All codes are available at https://github.com/NEUIR/ORION.git.

Fuzz testing is one of the most effective techniques for finding software vulnerabilities. While modern fuzzers can generate inputs and monitor executions automatically, the overall workflow, from analyzing a codebase, to configuring harnesses, to triaging results, still requires substantial manual effort. Prior attempts focused on single stages such as harness synthesis or input minimization, leaving researchers to manually connect the pieces into a complete fuzzing campaign. We introduce Orion, a framework that automates the the manual bottlenecks of fuzzing by integrating LLM reasoning with traditional tools, allowing campaigns to scale to settings where human effort alone was impractical. Orion uses LLMs for code reasoning and semantic guidance, while relying on deterministic tools for verification, iterative refinement, and tasks that require precision. Across our benchmark suite, Orion reduces human effort by 46-204x depending on the workflow stage, and we demonstrate its effectiveness through the discovery of two previously unknown vulnerabilities in the widely used open-source clib library.

For this week's Open Questions column, Cal Newport is filling in for Joshua Rothman. Much of the euphoria and dread swirling around today's artificial-intelligence technologies can be traced back to January, 2020, when a team of researchers at OpenAI published a thirty-page report titled "Scaling Laws for Neural Language Models." The team was led by the A.I. researcher Jared Kaplan, and included Dario Amodei, who is now the C.E.O. of Anthropic. They investigated a fairly nerdy question: What happens to the performance of language models when you increase their size and the intensity of their training? Back then, many machine-learning experts thought that, after they had reached a certain size, language models would effectively start memorizing the answers to their training questions, which would make them less useful once deployed.

Recent advances in web-augmented large language models (LLMs) have exhibited strong performance in complex reasoning tasks, yet these capabilities are mostly locked in proprietary systems with opaque architectures. In this work, we propose \textbf{ManuSearch}, a transparent and modular multi-agent framework designed to democratize deep search for LLMs. ManuSearch decomposes the search and reasoning process into three collaborative agents: (1) a solution planning agent that iteratively formulates sub-queries, (2) an Internet search agent that retrieves relevant documents via real-time web search, and (3) a structured webpage reading agent that extracts key evidence from raw web content. To rigorously evaluate deep reasoning abilities, we introduce \textbf{ORION}, a challenging benchmark focused on open-web reasoning over long-tail entities, covering both English and Chinese. Experimental results show that ManuSearch substantially outperforms prior open-source baselines and even surpasses leading closed-source systems. Our work paves the way for reproducible, extensible research in open deep search systems. We release the data and code in https://github.com/RUCAIBox/ManuSearch

Open rule refer to the implication from premise atoms to hypothesis atoms, which captures various relations between instances in the real world. Injecting open rule knowledge into the machine helps to improve the performance of downstream tasks such as dialogue and relation extraction. Existing approaches focus on single-hop open rule generation, ignoring multi-hop scenarios, leading to logical inconsistencies between premise and hypothesis atoms, as well as semantic duplication of generated rule atoms. To address these issues, we propose a progressive multi-stage open rule generation method called PRIMO. We introduce ontology information during the rule generation stage to reduce ambiguity and improve rule accuracy. PRIMO constructs a multi-stage structure consisting of generation, extraction, and ranking modules to fully leverage the latent knowledge within the language model across multiple dimensions. Furthermore, we employ reinforcement learning from human feedback to further optimize model, enhancing the model's understanding of commonsense knowledge. Experiments show that compared to baseline models, PRIMO significantly improves rule quality and diversity while reducing the repetition rate of rule atoms.