The crop of next-generation TVs arriving this year has more accurate colors than ever, thanks to a fancy new kind of backlighting. For how excellent they've come to look, today's televisions come with a brain-numbing assortment of acronyms for shoppers to parse. It's like the scariest dinner party I've ever attended. Remember LED, QLED, Mini LED, Micro LED, OLED, QD OLED? Sadly, all these acronyms do actually mean something, and this year's popular newcomer--RGB LED--implies shockingly accurate colors. Hiding behind upcoming panels from Hisense, Sony, Samsung, and LG announced at CES 2026, RGB LED (unhelpfully also called Micro RGB or RGB Mini LED) is the hot panel technology to talk about this year.

Existing benchmarks do not test language agents on their interaction with human users or ability to follow domain-specific rules, both of which are vital for deploying them in real world applications. We propose $\tau$-bench, a benchmark emulating dynamic conversations between a user (simulated by language models) and a language agent provided with domain-specific API tools and policy guidelines. We employ an efficient and faithful evaluation process that compares the database state at the end of a conversation with the annotated goal state. We also propose a new metric (pass^k) to evaluate the reliability of agent behavior over multiple trials. Our experiments show that even state-of-the-art function calling agents (like gpt-4o) succeed on <50% of the tasks, and are quite inconsistent (pass^8 <25% in retail). Our findings point to the need for methods that can improve the ability of agents to act consistently and follow rules reliably.

Now is a great time to replace that old screen. Modern TVs are brighter, have better contrast, and work better for gaming than ever before. You're in luck because we've found the best Prime Day TV deals on top WIRED-recommended TVs, soundbars, and 4K streaming devices. Whether you're gearing up to watch Lionel Messi in Major League Soccer or you're just trying to catch up on your favorite Marvel movies, these screens and accessories will be sure to satisfy. Updated July 12: We've added some fresh deals and updated prices. If you buy something using links in our stories, we may earn a commission.

Now is a great time to replace that old screen. Modern TVs are now brighter, have better contrast, and work better for gaming than ever before. This Prime Day we've found deals on some of our favorite TVs, soundbars, and 4K streaming devices. Whether you're gearing up to watch Lionel Messi in Major League Soccer or you're just trying to catch up on your favorite Marvel movies, these screens and accessories will be sure to satisfy. If you buy something using links in our stories, we may earn a commission.

NVIDIA has revealed G-Sync Ultra Low Motion Blur (ULMB) 2, the second generation of tech it designed to minimize motion blur in competitive games. Compared with ULMB, which it released in 2015, the company says the latest version offers nearly twice as much brightness, along with almost no crosstalk -- the strobing or double-image effect that sometimes appears when blur reduction features are enabled. Motion clarity is largely determined by the monitor's pixel response time. To improve matters, NVIDIA is using "full refresh rate backlight strobing," which builds on the backlight strobing technique from the original ULMB. Although the previous version of the tech improved motion clarity for many, it needed to switch off the monitor's backlight 75 percent of the time.

Starting at just $349 for the 43-inch model, the 4-Series is as affordable as it is flexible: This series runs the screen size gamut from 43 to 85 inches and even comes in software variants, with Roku (the version we tested), Google, and Android smart platforms available depending upon retailer and region. But no matter which one you buy, you're getting 4K resolution, HDR compatibility, and solid general picture quality. There are some reasons you might want to spend a bit more. This is an entry-level 4K TV, and despite being HDR compatible, it's simply not bright or colorful enough for good HDR performance. The basics of its picture are solid, but it's not equipped to be a great choice for current game consoles, and its backlight isn't powerful enough for especially bright rooms.

Glass is Sky's new voice-controlled streaming television – an ambitious attempt to ditch the satellite dish and provide pay TV straight to the screen, with no set top box required. The television comes in three sizes starting at £649 for a 43in screen, or £13 a month over four years, which works out at £25 cheaper too. Glass is a heavy beast, the 55in version weighs 28kg with its stand – about 10kg more than a standard 55in TV – but hides its bulk well from the front. The body is aluminium in a choice of five colours, and houses the built-in soundbar below the screen, making it look a bit like Apple's iMac. The 4K LCD screen ticks most of the specifications boxes.

First unveiled in 2018 at CES, LG is finally bringing its futuristic, rollable LG Signature OLED R 65-inch 4K TV to the US for the hefty sum of $100,000. According to LG's website, the television has an OLED screen, a Dolby Atmos and Sound Pro sound system and has both Google Assistant and Amazon's Alexa for built-in voice control. The 65-inch screen, which is described as a'revolutionary new experience,' gets tucked into aluminum housing unit when not in use, either for watching movies or playing video games. It has an OLED screen, a Dolby Atmos and Sound Pro sound system and both Google Assistant and Amazon's Alexa for built-in voice control The cabinet also has a Dolby Atmos sound system of its own. Manufactured in LG's Gumi facility, each TV is painstakingly assembled'with craftsman-like skill with attention to every detail', LG said last year.

Sony's new X800H is a major improvement over last year's G model, with interface tweaks and more powerful processing. Dolby Vision HDR and Dolby Atmos have been added to the mix, along with a redesigned remote control that finally looks like something that belongs with a Sony TV. With social distancing measures in place, my testing has been relocated from the TechHive lab to my home office, where the 65-inch X800H ($1,000) that Sony sent me for evaluation made for a tight squeeze. I'm guessing Sony sent this size because the 55-inch and smaller models don't have the fancy almond-shaped X-speakers that increase audio quality. I didn't hear the have-nots, so I can't comment on the difference, but the 65X800H's audio is definitely a step above the norm in this price range.

For the last several years, Vizio's M-Series has been a mainstay of TV value-hunters. The M-Series TVs (much like TCL's 6-Series) tend to give users the latest TV technology at much more affordable prices than the competition. To that end, 2019's M-Series Quantum delivers 4K resolution, an LED backlight with full-array local dimming technology, smart features, HDR and Dolby Vision compatibility, and--as you might have guessed from the name--quantum dots. Quantum dots are a newer TV tech that provide a big boost to a TV's color capabilities, and for the last several years they've really only been available in very high-end TVs from brands like Samsung and Sony. With the M-Series Quantum, Vizio is making this technology available to people who might not have $2,000 to spend on a new TV. Are the M-Series Quantum TVs perfect specimens? No--Vizio's learned how to cut just enough corners that, while nothing about them is too egregious, they're not as buttoned-up and posh-looking as their higher-price counterparts. Picture quality is the strongest foot forward here, while the design is nothing to speak of and elements of their software and behavior can be a bit frustrating.