selena gomez
Evaluating Long-Context Reasoning in LLM-Based WebAgents
Chung, Andy, Zhang, Yichi, Lin, Kaixiang, Rawal, Aditya, Gao, Qiaozi, Chai, Joyce
As large language model (LLM)-based agents become increasingly integrated into daily digital interactions, their ability to reason across long interaction histories becomes crucial for providing personalized and contextually aware assistance. However, the performance of these agents in long context scenarios, particularly for action-taking WebAgents operating in realistic web environments, remains largely unexplored. This paper introduces a benchmark for evaluating long context reasoning capabilities of WebAgents through sequentially dependent subtasks that require retrieval and application of information from extended interaction histories. We develop a novel evaluation framework that simulates multi-session user interactions by injecting irrelevant task trajectories between dependent subtasks, creating contexts ranging from 25,000 to 150,000 tokens. Through extensive evaluation of four popular models, Claude-3.7, GPT-4.1, Llama 4, and o4-mini, we observe a dramatic performance degradation as context length increases, with success rates dropping from 40-50\% in baseline conditions to less than 10\% in long context scenarios. Our detailed error analysis reveals that agents primarily fail due to getting stuck in loops and losing track of original task objectives. We further propose an implicit RAG approach that provides modest improvements by generating task-relevant summaries, though fundamental limitations in long context reasoning persist. These findings highlight critical challenges for deploying WebAgents in realistic, long-term user interaction scenarios and provide insights for developing more robust agent architectures capable of maintaining coherent task execution across extended contexts.
- North America > The Bahamas (0.14)
- North America > United States > New York (0.04)
- North America > United States > Florida > Miami-Dade County > Miami (0.04)
- (11 more...)
- Workflow (0.93)
- Research Report > New Finding (0.93)
- Media (1.00)
- Consumer Products & Services (1.00)
- Transportation (0.93)
- Leisure & Entertainment > Sports > Basketball (0.46)
Space agency breaks silence on 'foreign' interstellar object soaring past Mars: 'A rare visitor'
Dolly Parton's sister asks for prayers for music icon, 79, amid mystery health battle Bloodcurdling videos shows girl aged 12 subway surfing days before she and friend, 13, died during 3.10am stunt Trump's mass deportation effort removed staggering amount of migrants from US in first year of term: 'Just the beginning' Mom-of-two hospitalized, her son left suicidal and their dog dead... after a simple mistake turns $500K home into a death trap Popular actress shocks fans with'unrecognizable' appearance after suffering heartbreaking tragedy Selena Gomez's'disgusting' habit on her wedding day exposed by eagle-eyed fans despite star's efforts to hide it Charlie Kirk leaked text confirms he was livid about'bullying' Jewish donors: 'I'm leaving pro-Israel cause' She's accused of'murder-for-hire' plot against her famous TV star husband. Now there's a shock twist in the case... and she's forced to stare her demons in the face Man is arrested on terror charges over disturbing Halloween display of fake body bags with town official's titles Space agency breaks silence on'foreign' interstellar object soaring past Mars: 'A rare visitor' 'Disneyland of grocery stores' reveals items most hit by tariffs and the fan favorite it STOPPED buying from China Space agency breaks silence on'foreign' interstellar object soaring past Mars: 'A rare visitor' READ MORE: Mysterious interstellar visitor spotted above Mars appears as'massive cylindrical craft' The European Space Agency (ESA) has finally shared new details about the mysterious interstellar visitor days after its closest approach to Mars . The object, dubbed 3I/ATLAS, came within 18.6 million miles of the Red Planet on October 3, and while NASA quickly uploaded images captured by its Perseverance rover on the Martian surface, ESA had remained quiet until now . The ESA's ExoMars Trace Gas Orbiter (TGO) captured images of the object, appearing as a tiny, blurry white dot in a series of images. The object's icy nucleus and its surrounding halo of gas and dust, called a coma, could not be distinguished separately, but the faint glow was clearly visible against the blackness of space.
- Asia > China (0.24)
- Asia > Middle East > Israel (0.24)
- North America > Canada > Alberta (0.14)
- (16 more...)
- Media > Television (1.00)
- Media > Music (1.00)
- Media > Film (1.00)
- (5 more...)
Do you have one of these gathering dust in your attic? Experts reveal the forgotten gadgets that could be worth a fortune - including answering machines for landlines
Dolly Parton's sister asks for prayers for music icon, 79, amid mystery health battle Charlie Kirk leaked text confirms he was livid about'bullying' Jewish donors: 'I'm leaving pro-Israel cause' Mom-of-two hospitalized, her son left suicidal and their dog dead... after a simple mistake turns $500K home into a death trap Trump's mass deportation effort removed staggering amount of migrants from US in first year of term: 'Just the beginning' Man is arrested on terror charges over disturbing Halloween display of fake body bags with town official's titles Selena Gomez's'disgusting' habit on her wedding day exposed by eagle-eyed fans despite star's efforts to hide it Popular actress shocks fans with'unrecognizable' appearance after suffering heartbreaking tragedy She's accused of'murder-for-hire' plot against her famous TV star husband. Now there's a shock twist in the case... and she's forced to stare her demons in the face Bloodcurdling videos shows girl aged 12 subway surfing days before she and friend, 13, died during 3.10am stunt'Kissing Trump's a**': President mocks Canada's obsequious PM as he begs for tariff relief Keith Urban's guitarist Maggie once vowed to'never' date a tour mate... as she's accused of charming Nicole Kidman's ex Hollywood's favorite muscle car primed for return as America's No.1 automaker files secret paperwork Do you have one of these gathering dust in your attic? It was only a couple of decades ago that homes and offices were filled with answering machines and BlackBerry phones. And although they've been obsolete for years, they're now among the retro gadgets that could make you a fortune. Brits are sitting on a hidden goldmine of old forgotten tech devices that may be gathering dust in the attic, according to a new report from Gumtree.
- Asia > Middle East > Israel (0.24)
- North America > Canada > Alberta (0.14)
- North America > United States > New York (0.04)
- (21 more...)
- Transportation (1.00)
- Media > Television (1.00)
- Media > Music (1.00)
- (8 more...)
- Information Technology > Communications > Social Media (1.00)
- Information Technology > Artificial Intelligence (1.00)
- Information Technology > Communications > Mobile (0.96)
- Information Technology > Hardware (0.68)
'Meteor' streaks through Britain's skies tonight leaving lucky gazers in awe
Charlie Kirk leaked text confirms he was livid about'bullying' Jewish donors: 'I'm leaving pro-Israel cause' White House insider who says WAR with Venezuela is inevitable... as Trump's lethal options are laid out I've seen the real Victoria Beckham... her actions gave me PTSD, she shunned me and even banned me from glancing in her direction. Jimmy Kimmel's audience boom comes crashing down as he loses 71% of viewers in one week'Kissing Trump's a**': President mocks Canada's obsequious PM as he begs for tariff relief World's most invasive predator terrorizing East Coast is delicious and should be eaten to stop its spread, experts say I've had enough of the arrogant and entitled fat brigade. Bloodcurdling videos shows girl aged 12 subway surfing days before she and friend, 13, died during 3.10am stunt Another blow for Prince Harry as African country cuts ties with his'disrespectful' charity Friends fear for new CBS News boss Bari Weiss, claiming her wife thinks she sold out... and her new job will'consume her life' Keith Urban's guitarist Maggie once vowed to'never' date a tour mate... as she's accused of charming Nicole Kidman's ex Hollywood's favorite muscle car primed for return as America's No.1 automaker files secret paperwork AMANDA PLATELL: I never thought I'd feel sorry for Harry. There's one thing he'd do anything to defend... and now Meghan's trampled all over it Ben Affleck's VERY familiar whispers to Jennifer Lopez on the red carpet revealed... as their romantic new era sends fans into overdrive Jimmy Kimmel continues anti-Trump rants and says he's more popular with Americans than the president Brits have been left in awe after spotting what is believed to be a'meteor' glowing through the night sky. Lucky stargazers in Northfields and West Ealing, west London, have reported seeing a blue-ish green blob race through the city's sky tonight.
- Asia > Middle East > Israel (0.24)
- South America > Venezuela (0.24)
- North America > Canada > Alberta (0.14)
- (16 more...)
- Media > Television (1.00)
- Media > Music (1.00)
- Media > Film (1.00)
- (3 more...)
Top-secret US spy jet spotted circling Russia amid mounting WW3 fears
'Kissing Trump's a**': President mocks Canada's obsequious PM as he begs for tariff relief World's most invasive predator terrorizing East Coast is delicious and should be eaten to stop its spread, experts say Clash of the White House titans: Two of Trump's most powerful lieutenants go to WAR with each other - after vicious leak sent shockwaves AMANDA PLATELL: I never thought I'd feel sorry for Harry. There's one thing he'd do anything to defend... and now Meghan's trampled all over it White House insider who says WAR with Venezuela is inevitable... as Trump's lethal options are laid out Jimmy Kimmel's audience boom comes crashing down as he loses 71% of viewers in one week Lynn put her strange symptoms down to being a busy mum. AOC hit by shockingly crude sex insult by White House after she mocked'TINY' Stephen Miller Friends fear for new CBS News boss Bari Weiss, claiming her wife thinks she sold out... and her new job will'consume her life' Biden ordered CIA cover-up of his'corrupt' business ties to Ukraine, astonishing secret files show We've lost FOURTEEN stone on weight-loss jabs... and it's changed our lives in ways you'd NEVER expect. Jerry Jones slapped with fine by NFL for making rude gesture to fans... but Cowboys owner gives baffling excuse And a humiliating lifeline: Backroom secrets of Taylor Swift and Blake Lively... after hit new song Inside the rise of'kidfluencers' and the hidden toll of turning childhood into million-dollar content A US Air Force jet designed to collect intelligence on enemy radar systems was spotted making circles over Russia, following rising tensions with Moscow . Flight tracking data showed the RC-135U'Combat Sent' taking off from England early Tuesday, flying over the Baltic states and looping around Kaliningrad, the Russian exclave between Poland and Lithuania, before returning to the UK.
- Transportation > Air (1.00)
- Media > Television (1.00)
- Media > Music (1.00)
- (4 more...)
Millions of Americans under dangerous freeze warning TODAY as temperatures plunge to 22 F
Ominous warning for humanity as birds suddenly adopt'unsettling' behavior Meghan is accused of'giggling as model stumbles on the catwalk': More Paris Fashion Week disasters emerge, including awkward moment with Kristin Scott Thomas More girls are starting their periods younger than ever before - scientists think they've finally found what's causing it The TRUTH to the doting mother who slaughtered her children and husband told by those she'd been quietly tormenting for years Insiders confirm what everyone suspects about Taylor Swift and Blake Lively... the private apology... and how any future friendship hangs on one humiliating condition Outrage as Baltimore's Dem mayor spends $164k of taxpayer cash on ultra-luxurious new SUV I have no sympathy for them - but this disturbing new trend isn't the answer: JANA HOCKING Taylor Swift reveals truth behind raunchy song about Travis Kelce's manhood Revealed: Which slimming jab REALLY works best. The doctors' ultimate expert guide on which to pick, how to save money, beat every side effect... and what you need to know about the'golden dose' Functioning alcoholics hide in plain sight... so are YOU one? Trump brands NFL's Bad Bunny Super Bowl halftime show selection'absolutely ridiculous' The troubled background of delivery man stabbed by Mark Sanchez... as he launches million-dollar lawsuit and sparks civil war at Fox Millions of Americans are facing a dangerous freeze warning on Tuesday as temperatures drop below freezing across multiple states. Sub-freezing temperatures as low as 22 to 30 F are expected in parts of Wisconsin, Minnesota, North Dakota, South Dakota, Michigan, Colorado, Wyoming and Idaho . The National Weather Service (NWS) issued the warning for tonight into Wednesday morning, ending between 8 and 10am local time, depending on the state and county .
- North America > United States > Wisconsin (0.61)
- North America > United States > North Dakota (0.61)
- North America > United States > Minnesota (0.61)
- (16 more...)
- Transportation > Air (1.00)
- Media > Television (1.00)
- Media > Music (1.00)
- (4 more...)
That was close! Huge asteroid comes within 300 miles of hitting Earth - and NASA only noticed AFTER the close encounter
Ominous warning for humanity as birds suddenly adopt'unsettling' behavior Meghan is accused of'giggling as model stumbles on the catwalk': More Paris Fashion Week disasters emerge, including awkward moment with Kristin Scott Thomas More girls are starting their periods younger than ever before - scientists think they've finally found what's causing it The TRUTH to the doting mother who slaughtered her children and husband told by those she'd been quietly tormenting for years Insiders confirm what everyone suspects about Taylor Swift and Blake Lively... the private apology... and how any future friendship hangs on one humiliating condition Outrage as Baltimore's Dem mayor spends $164k of taxpayer cash on ultra-luxurious new SUV I have no sympathy for them - but this disturbing new trend isn't the answer: JANA HOCKING Taylor Swift reveals truth behind raunchy song about Travis Kelce's manhood Trump stuns CNN reporter as he muses about Ghislaine Maxwell pardon: 'I haven't heard that name in so long' Revealed: Which slimming jab REALLY works best. The doctors' ultimate expert guide on which to pick, how to save money, beat every side effect... and what you need to know about the'golden dose' Functioning alcoholics hide in plain sight... so are YOU one? Trump brands NFL's Bad Bunny Super Bowl halftime show selection'absolutely ridiculous' The troubled background of delivery man stabbed by Mark Sanchez... as he launches million-dollar lawsuit and sparks civil war at Fox A huge asteroid came within 300 miles of hitting Earth, and scientists only noticed after it had already skimmed past the planet. The 9.8-foot (three metre) space rock, dubbed 2025 TF, flew over Antarctica in the early hours of October 1. Passing at an altitude of just 265 miles (428 kilometres), the rock came closer to the Earth's surface than the orbit of the International Space Station . However, space agencies only realised the near-miss had occurred when the asteroid was detected by the Catalina Sky Survey a few hours later.
- Antarctica (0.24)
- North America > Canada > Alberta (0.14)
- North America > United States > California > Los Angeles County > Los Angeles (0.04)
- (12 more...)
- Transportation > Air (1.00)
- Media > Television (1.00)
- Media > Music (1.00)
- (5 more...)
People who don't like animals are more likely to have dark personality traits, study finds
Ominous warning for humanity as birds suddenly adopt'unsettling' behavior Meghan is accused of'giggling as model stumbles on the catwalk': More Paris Fashion Week disasters emerge, including awkward moment with Kristin Scott Thomas More girls are starting their periods younger than ever before - scientists think they've finally found what's causing it The TRUTH to the doting mother who slaughtered her children and husband told by those she'd been quietly tormenting for years Insiders confirm what everyone suspects about Taylor Swift and Blake Lively... the private apology... and how any future friendship hangs on one humiliating condition Outrage as Baltimore's Dem mayor spends $164k of taxpayer cash on ultra-luxurious new SUV I have no sympathy for them - but this disturbing new trend isn't the answer: JANA HOCKING Taylor Swift reveals truth behind raunchy song about Travis Kelce's manhood Trump stuns CNN reporter as he muses about Ghislaine Maxwell pardon: 'I haven't heard that name in so long' Revealed: Which slimming jab REALLY works best. The doctors' ultimate expert guide on which to pick, how to save money, beat every side effect... and what you need to know about the'golden dose' Functioning alcoholics hide in plain sight... so are YOU one? Trump brands NFL's Bad Bunny Super Bowl halftime show selection'absolutely ridiculous' The troubled background of delivery man stabbed by Mark Sanchez... as he launches million-dollar lawsuit and sparks civil war at Fox People who don't like animals are more likely to have dark personality traits, study finds On-screen psychopaths such as Patrick Bateman in'American Psycho' and Villanelle in ' Killing Eve ' are often depicted hurting animals. Now, a study suggests this character flaw is not just the stuff of fiction. Scientists in Serbia have found a link between psychopathy and the belief that animals aren't as worthy as humans.
- North America > Canada > Alberta (0.14)
- North America > United States > California > Los Angeles County > Los Angeles (0.04)
- Asia > Middle East > Republic of Türkiye (0.04)
- (13 more...)
- Personal (0.46)
- Research Report > Experimental Study (0.34)
- Media > Music (1.00)
- Media > Film (1.00)
- Leisure & Entertainment > Sports > Football (1.00)
- (2 more...)
Is YOUR dog a genius? Vets reveal the five simple tests that prove if your pooch is gifted
There are two big reasons why I don't believe the official 9/11 story, Charlie Sheen tells Tucker Carlson Today is Selena Gomez's wedding. But a bridezilla decision and weeks of family feuding have left her mother utterly'shattered'... and now insiders are spilling everything Disturbing twist in case of cheerleader whose dead baby was found in closet: 'There were whimpers' How Prince Harry collapses'like a souffle' as Meghan Markle interrupts him multiple times during an interview, body language expert reveals LIZ JONES: I have history with Colin Firth's ex-wife Livia. Now, her petulant protest over Trump's UK state visit proves something humiliating about her Ryder Cup fans left appalled by'criminal' Uber prices to get home from Bethpage Black: 'Just gonna walk' How people are being hanged from cranes and strangled to death over 45 minutes while crowds of excited families watch as part of Iran's mass execution campaign that's killed more than 1,000. And the death penalty for girls starts at just 9... Midwestern airport with'outstanding food' is'best' for traveler satisfaction Teacher dies from overdose before he's due to be sentenced for murdering his wife I'm the witch who cursed Charlie Kirk. 'Hamptons of the North' loved by celebs in battle over Russian developer's Maldives-style resort plan NFL fan labeled the new'Phillies Karen' after being caught on camera stealing young boy's gift from Patrick Mahomes Princess Eugenie puts on a brave face as she releases her first statement since Sarah Ferguson's leaked email to Jeffrey Epstein Prince Harry'taken by surprise' by how'formal' his 53-minute meeting with King Charles proved - amid claims he will be blocked from'half-in, half-out' return to Royal Family fold despite handing over Meghan and children photo Is YOUR dog a genius?
- Asia > Middle East > Iran (0.24)
- Asia > Maldives (0.24)
- North America > Canada > Alberta (0.14)
- (18 more...)
- Media > Television (1.00)
- Media > Music (1.00)
- Media > Film (1.00)
- (5 more...)
The Sidemen's reality show, and Selena Gomez's 'love story' album: What to stream this week
Since 2007 the Assassin's Creed series has allowed players to hack, slash and sneak their way through a range of historical settings. And the latest instalment, Shadows, creeping on to PS5, Xbox and PC from Thursday, grants fans' long-held wish for an adventure set in feudal Japan. It mixes the stealth gameplay of the recent Assassin's Creed Mirage with the combat-focused approach of mega-hit Valhalla and throws ninjas into the mix. But it's being seen by many as a make-or-break title for French publisher Ubisoft, one of the biggest gaming companies in the world. After a lacklustre 2024, there's a lot of hope that the twice-delayed Shadows will replicate the sales of previous games in the Assassin's Creed series.