Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process. WebThinker integrates a Deep Web Explorer module, enabling LRMs to dynamically search, navigate, and extract information from the web when encountering knowledge gaps. It also employs an Autonomous Think-Search-and-Draft strategy, allowing the model to seamlessly interleave reasoning, information gathering, and report writing in real time. To further enhance research tool utilization, we introduce an RL-based training strategy via iterative online Direct Preference Optimization (DPO). Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems. Our approach enhances LRM reliability and applicability in complex scenarios, paving the way for more capable and versatile deep research systems.

Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization. In this work, we introduce Topological Evolution Rate (TopER), a novel, lowdimensional embedding approach grounded in topological data analysis.

"You would not believe the texts I got from these tech guys," NYT reporters Maggie Haberman and Jonathan Swan quote Donald Trump as telling associates in an upcoming book. Meta CEO Mark Zuckerberg and Amazon founder Jeff Bezos sought to ingratiate themselves with President Donald Trump after he won the 2024 election, and in return he mocked their efforts behind their backs, according to a new book by The New York Times reporters Maggie Haberman and Jonathan Swan. Zuckerberg once texted Trump a photo of a letter written by one of his grade-school-age children, who wrote that they "looked forward to the golden age of America," a slogan Trump had repeated at rallies during the presidential campaign. And over dinner at Trump's Mar-a-Lago club, Bezos denigrated The Washington Post to Trump and essentially described the newspaper as one of his worst financial investments, months before he unsuccessfully sought a business favor from the president. These episodes are detailed in the book, a copy of which WIRED obtained ahead of its release on June 23.

Inside America's new fattest town: Burgers are the size of your head, gyms lie empty and custom mobility scooters carry 800lb loads... as we investigate why Ozempic just DOESN'T work Ex-partner of dad who was berated for taking his daughters into women's bathroom claims he'exploited' girls and accuses him of failing to pay child support... before he hits back The'marry me' sex move that'll make even the most commitment-phobic of men beg to see you again... and it worked for THREE of my friends Stingy fast food giant named America's favorite restaurant AGAIN... and experts think they know why Netherlands vs Sweden - World Cup Group F LIVE: Liverpool's Cody Gakpo adds to Brian Brobbey's quickfire double as Ronald Koeman's side aim for first win Meghan went into'high-performance mode' when Serena Williams's mother'ignored her' at the US Open, body language expert claims - as visit to the UK raises the intriguing possibility of the Duchess attending Wimbledon Dua Lipa stuns in a bespoke Chanel bridal gown and parties into the early hours as she shares the first pictures from her £1.5million Little-known penis condition that SHORTENS manhood: Shockingly, 1 in 10 men have it... but most miss the signs until it's too late to reverse with easy cure: DR PETAR BAJIC Jeremy Clarkson, 66, reveals he is in remission after being diagnosed with'aggressive' prostate cancer as he says he's the'world's luckiest man' Capitol Hill glam girl shares the beauty secrets of Trump's leading ladies... from go-to makeup products to tips on achieving the perfect'Mar-A-Lago face' Harrowing chain of events behind The Ring star's death at just 35 laid bare by doctors in agonizing detail... and how it could have been prevented The four mistakes that led to bungee tragedy on Skeleton Bridge: FRED KELLY saw the scene for himself, now he retraces the prelude to disaster. So was it really an accident? Taylor Swift's bombshell wedding invite'olive branch' to Blake Lively: Insiders reveal every detail of reconciliation literally no one saw coming... and the actress has a dress picked out! Furious Trump hits back at Italian Prime Minister Meloni and gives her unusual'nickname' as their photo feud ramps up World Cup commentator denies making racist comment about Ciara live on air during USA's win over Australia TV star mom, 46, who appeared on'quitting everything to change your life' show died in fire at luxury Caribbean beach resort that sent 1,700 tourists running for their lives Swedish actress, 81, was in TWO James Bond movies and also worked with Charlton Heston, who is she?

The success of Graph Neural Networks (GNNs) leverages the homophily principle, where connected nodes share similar features and labels. However, this assumption breaks down in heterophilic graphs, where same-class nodes are often distributed across distant neighborhoods rather than immediate connections. Recent attempts expand the receptive field through multi-hop aggregation schemes that explicitly preserve intermediate representations from each hop distance. While effective at capturing heterophilic patterns, these methods require separate weight matrices per hop and feature concatenation, causing parameters to scale linearly with hop count. This leads to high computational complexity and GPU memory consumption. We propose Gated Multi-hop Message Passing (GAMMA), where nodes assess how relevant the aggregated information is from their k-hop neighbors. This assessment occurs through multiple refinement steps where the node compares each hop's embedding with its current representation, allowing it to focus on the most informative hops. During the forward pass, GAMMA finds the optimal mix of multi-hop information local to each node using a single feature vector without needing separate representations for each hop, thereby maintaining dimensionality comparable to single hop GNNs. In addition, we propose a weight sharing scheme that leverages a unified transformation for aggregated features from multiple hops so the global heterophilic patterns specific to each hop are learned during training.

A Florida man is suing several law enforcement agencies for his arrest and prosecution for allegedly luring a child after he was wrongly identified using faulty AI facial recognition software. According to the Jacksonville Beach police department, an algorithm returned a 93% probability that Robert Dillon was the man caught on security cameras at a McDonald's in the town attempting to persuade an unaccompanied girl, aged younger than 12, to leave with him. Dillon, however, lives in Fort Myers, more than 300 miles and a five-hour drive away, and told detectives he had never been to Jacksonville Beach in his life. The case was dismissed and charges dropped last year over the August 2024 incident. Now the 52-year-old has filed a lawsuit against the police department, the Jacksonville sheriff's office, and Bob Gualtieri, the sheriff of Pinellas county, whose agency maintains and operates the Faces (Face Analysis Comparison and Examination) system and leases it to other law enforcement.

The ACLU is suing two Florida police departments over the arrest of a Fort Myers man in a child-abduction case, saying officers treated a flawed face recognition match as a near-certain ID. A Florida man was wrongfully arrested for attempting to illegally lure a child after police relied on a face recognition match that was inaccurate, according to a lawsuit filed on Wednesday, even though he lived more than 300 miles from the scene and says he had never set foot in the city where the crime took place. Robert Dillon, a 52-year-old commercial crabber from Fort Myers, was arrested after FACES--a face recognition system operated by Florida's Pinellas County Sheriff's Office--matched his face against a photo of a man on a computer screen taken with a cellphone. The system returned a "93 percent match on facial features," according to police investigatory notes. The scores it emits represent how much two images look alike to the algorithm.

Alex Vindman Survived Trump's Retaliation Machine. In 2019, Alex Vindman testified during President Trump's first impeachment trial--a decision that ended his military career. Now he wants to challenge the president from the halls of Congress. Alex Vindman knows a thing or two about pissing off President Donald Trump . In 2019, Vindman rose to national prominence when he served as a witness during Trump's first impeachment trial. If you've lost track of that particular scandal, it's the one involving Trump, Ukrainian president Volodymyr Zelensky, the Biden family and Vindman listening in on a troubling phone call in his capacity as the director for European affairs on the National Security Council. Vindman's congressional testimony describing that pivotal call was widely lauded, even as it ended his storied military career: After being ousted from the NSC, Vindman retired from the Army in 2020. Six years later, he's got his eye on another governmental gig. In January, Vindman announced plans to challenge Republican incumbent Ashley Moody for the Florida seat in the US Senate previously held by Marco Rubio. Vindman, who tells me he moved to Florida in 2023 because his wife wanted to politics, is the latest candidate I'm chatting with ahead of the November midterms. He's particularly interesting to me, and WIRED, for a few reasons: Vindman has lived through--and emerged from--the Trump retaliation machine, and I wanted to hear more about that journey; he's been vocal about his opposition to both the war in Iran and ICE, two topics we cover frequently; and I wanted his view, as a longtime service member, on AI through the lens of national security. Then there's the fact that Vindman, running in what's ostensibly a Republican stronghold, has a decent shot at winning the damn thing: Though Senator Moody still leads in most polls, Vindman is often within spitting distance--no small feat for a first-time candidate whose campaign started around five months ago. KATIE DRUMMOND: Welcome to the Big Interview, Alex. Good to be here with you, Katie. So glad to have you here. You are maybe best known on a national level as a whistleblower, but you were also an Army veteran of more than 20 years. You were honored with a Purple Heart after being wounded in Iraq, and you were on the National Security Council.

Caitlyn Jenner biographer and Robin Riker's ex William Hasley found dead on hiking trail at 78 Karmelo Anthony's mother sobs with shock as son is found guilty of murdering Austin Metcalf, 17, in stabbing that horrified America: Live updates Disgraceful texts'hot' teacher sent boy, 17, who she had illegal sex with where she moaned about her HUSBAND Everyone always said I cleared my throat a lot. But then I developed shoulder pain and doctors discovered the sinister cause... the world's deadliest cancer. Don't leave it too late like I did Moment Real Housewives star Lenny Hochstein's sexual assault accuser'dances' as she leaves Star Island mansion - before filing $100k civil lawsuit Leaked transcript of UNAIRED 60 Minutes interview exposes REAL reason'callous' CBS star Scott Pelley'deserved to be fired' Urgent recall for 1.1m vehicles over fears they could spontaneously CATCH FIRE even when parked Disturbing new death scene photos show tech whistleblower's haunting final moments... as forensic report casts doubt on suicide claims: 'Execution angle' 'Great' mom, 32, tried to gas herself and her three young kids to death after inviting them to'popcorn sleepover' in car, prosecutors allege The porn-fuelled fantasy middle-class husbands are desperate to try with their wives... and it almost always ends in divorce: JANA HOCKING The historic steel mill that helped build America was written off for dead. John Oliver's private panic: Late-night curse spreads and host prepares for worst as insiders reveal his desperate'plan B'... and the industry whispers swirling about his fate Woke Vegas school compared boy to racist cross burner over pro-ICE stickers and expelled him... but did not punish pro-migrant students for class walkout, lawsuit alleges Medical student, 24, died by suicide in his white coat a day after he was suspended for alleged'inappropriate' behavior towards female patient, lawsuit alleges, as his heartbreaking goodbye note to parents is revealed Mother's final words before she was shot dead'by new husband' in front of her two young children All the backstage gossip from Miami Swim Week: Insider exposes'catty' VIP's diva demands... STEALING... and'morbidly embarrassing' celeb moment everyone is whispering about A strong earthquake that struck the Gulf of America on Monday, sending shockwaves hundreds of miles away into Florida. A 6.1 magnitude was detected west-northwest of Mantua, Cuba, with shaking reported as far north as Tallahassee.

Logged advertising auctions make offline reserve-price evaluation attractive but risky. Replay tables can identify policies with large apparent yield gains, yet they can also hide weak threshold support, multiple-comparison effects, subgroup harm, and bidder-response uncertainty. Existing replay and off-policy evaluation methods estimate or rank policy values, but they do not directly answer the operational question of whether the available evidence is strong enough to justify validation. This paper develops a support-aware offline decision framework for reserve-policy selection. Rather than outputting a single point-estimate winner, the framework converts logged evidence into a conservative decision object consisting of certified policies, statistically dominated alternatives, and unresolved candidates requiring further validation. The main theoretical result gives a unified finite-catalog guarantee showing that, under simultaneous uncertainty control and conservative support gates, the framework preserves the best gate-passing policy while eliminating only policies with certified regret. Supporting results characterize support-localized replay generalization, establish information-theoretic threshold-resolution limits, and quantify when heterogeneous bidder response can overturn localized replay rankings. Experiments on iPinYou real-time-bidding logs show that the leading reserve rule achieves a 47.66% replay lift in season two, a 40.71% simultaneous lower-bound lift, and a 43.87% frozen out-of-time replay lift in season three. The framework reduces a 19-policy catalog to a two-policy validation shortlist while certifying non-harm across 44 advertiser, exchange, and region segments. The results support the central claim that offline reserve-policy evaluation should produce certified validation decisions rather than point-estimate rankings alone.