Goto

Collaborating Authors

 Media


Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

arXiv.org Artificial Intelligence

The rapid emergence of diverse large language models (LLMs) has spurred the development of LLM routers that assign user queries to the most suitable model. However, existing LLM routers typically perform a single-round, one-to-one mapping (\textit{i.e.}, assigning each query to a single model in isolation), which limits their capability to tackle complex tasks that demand the complementary strengths of multiple LLMs. In this paper, we present \textbf{Router-R1}, a reinforcement learning (RL)-based framework that formulates multi-LLM routing and aggregation as a sequential decision process. Router-R1 instantiates the router itself as a capable LLM, leveraging its reasoning ability to interleave "think" actions (internal deliberation) with "route" actions (dynamic model invocation), and integrates each response into its evolving context. To facilitate learning, we employ a lightweight rule-based reward comprising format rewards, final outcome rewards, and a novel cost reward for optimizing the balance between performance and cost, opening a pathway toward enhancing performance-cost trade-offs via RL. Router-R1 also conditions only on simple model descriptors such as pricing, latency, and example performance, enabling strong generalization to unseen model selection. Experiments on seven general and multi-hop QA benchmarks show that Router-R1 outperforms several strong baselines, achieving superior performance while maintaining robust generalization and cost management.


Labor rules out giving tech giants free rein to mine copyright content to train AI

The Guardian

The attorney general, Michelle Rowland, will confirm the decision on Monday, shutting the door on the proposal floated by the Productivity Commission and backed by tech companies. The attorney general, Michelle Rowland, will confirm the decision on Monday, shutting the door on the proposal floated by the Productivity Commission and backed by tech companies. The Albanese government has explicitly ruled out handing tech companies free rein to mine creative content to train their artificial intelligence models, after a fierce backlash from authors and arts and media groups. The attorney general, Michelle Rowland, will confirm the decision on Monday, shutting the door on a contentious proposal floated by the Productivity Commission and backed by tech companies. "Australian creatives are not only world class, but they are also the lifeblood of Australian culture, and we must ensure the right legal protections are in place," Rowland said.


Troublemaking weather pattern is BACK spelling disaster for winter with threat of flooding and wildfires

Daily Mail - Science & tech

Two arrested over Louvre'heist of the century' after raid of France's £76million crown jewels Tupac's humiliating intimate disfigurement revealed... and how his lies to cover it up led to his murder Virginia Giuffre's ex boyfriend says she was terrified'shaking with fear' after sex with Prince Andrew fearing'something would happen to her' I've started having heart palpitations. Psychotherapist explains why No Kings rallies consisted of mostly'educated white women' 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 Inside Prince Harry and Meghan's final night of freedom at a Halloween party with Princess Eugenie just hours before news of their relationship broke Kristen Bell's friends turn on her with savage disclosures: Insiders reveal poisonous whispers behind her back... as she goes into full diva mode Influencer, 23, speaks out after being arrested for'running interstate drug smuggling network' Kim Kardashian's just been caught in a despicable lie. She can cry all she wants... there's no hiding the truth now: CAROLINE BULLOCK Meghan Markle's fashion faux pas that shocked onlookers during her first overseas tour just months after marrying Prince Harry Inside Andrew's family summit: How Fergie wailed and'melted down' at title loss, Beatrice and Eugenie were'blindsided' and now daughters' assets face'ethics check' to avoid more scandal: BARBARA DAVIES Flamboyant art dealer whose'fake Warhols fooled' Florida's elite is out on bond and cashing in on a flashy new fad Californians being urged to take up arms to deal with'aggressive' invasive species attacking children A disturbing weather pattern could wreak havoc across the US at the end of this year's hurricane season, experts have warned. November tropical storms may be affected by La Nin a, according to Matthew Rosencrans, the lead hurricane seasonal forecaster with the National Oceanic and Atmospheric Administration (NOAA). La Nin a is part of a natural climate cycle known as El Nin o-Southern Oscillation Neutral (ENSO), which alternates between warmer and cooler seawater along the equator in the Pacific Ocean.


People are talking with 'AI Jesus.' But do they have a prayer?

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .


Bloody Mary, Bloody Mary, Bloody Mary: How the classic sleepover party game really CAN summon a ghost in your mirror

Daily Mail - Science & tech

Tupac's humiliating intimate disfigurement revealed... and how his lies to cover it up led to his murder I've started having heart palpitations. 'Black Ivy League' university looks to expand into crime-riddled Oakland Kristen Bell's friends turn on her with savage disclosures: Insiders reveal poisonous whispers behind her back... as she goes into full diva mode Shooting leaves two dead and 11 injured at large house party with'underage people' in North Carolina Kim Kardashian's just been caught in a despicable lie. She can cry all she wants... there's no hiding the truth now: CAROLINE BULLOCK 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 Prosecutor who declined to charge Letitia James with bank fraud fired after'mishandling evidence' Californians being urged to take up arms to deal with'aggressive' invasive species attacking children Inside Andrew's family summit: How Fergie wailed and'melted down' at title loss, Beatrice and Eugenie were'blindsided' and now daughters' assets face'ethics check' to avoid more scandal: BARBARA DAVIES LIZ JONES: I was devastated when my husband cheated. But here's the reason part of me was secretly glad that every woman over-50 will understand Psychotherapist explains why No Kings rallies consisted of mostly'educated white women' Tree optical illusion messes with your mind - you can see the squirrel but can you spot the cat in 30 seconds? Turn off the lights, burn a candle, look into the mirror and say the magic words: 'Bloody Mary, Bloody Mary, Bloody Mary'.



4 tasks every aging American must do right now

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .


Shocking video you MUST watch before voting for Mamdani: Here's what will become of NYC under him... and it's worse than everyone fears

Daily Mail - Science & tech

Stunning before-and-after photos show the seven most dramatic changes in Trump's controversial White House makeover She was a respected Teacher of the Year finalist... until she lost everything when Charlie Kirk was killed. Inside Andrew's family summit: How Fergie wailed and'melted down' at title loss, Beatrice and Eugenie were'blindsided' and now daughters' assets face'ethics check' to avoid more scandal: BARBARA DAVIES I have no sympathy for Britney Spears. What if her latest stunt had killed a kid? It's time to admit the truth about this public menace: KENNEDY'Nazi texts' leakers UNMASKED: Alleged White House saboteurs are finally exposed... and so is their twisted motive for destroying political prodigy Extraordinary story behind GM's decision to ax much-loved CarPlay... and sinister reason ALL manufacturers will follow What is Charcot-Marie-Tooth disease... the devastating condition that killed 9-1-1 Nashville actor Isabelle Tate Bijou Phillips files to change daughter's name after ex Danny Masterson's rape conviction Treasure hunters seeking Nazi gold worth £200MILLION believe they have'found the real thing' after'monumental' discovery under remains of SS palace'brothel' Former Gambino mob boss'Sammy the Bull' Gravano reveals the truth behind the NBA betting scandal My wife won't get a job and I feel broken trying to provide for our family. Hold on, says DEAR CAROLINE... that's bad enough but your letter raises a MUCH bigger red flag I got the body of my dreams at 51 by following 9 simple rules, says beauty guru ROSIE GREEN.


13 riveting images from the 2025 Wildlife Photographer of the Year awards

Popular Science

From a hyena stalking an abandoned diamond mining town to a pile of seething rattlesnakes. Dennis had been keeping an eye out for wild cats such as servals for several days when a call came over the radio: one had been seen at Ndutu Lake. It was a caracal, successfully hunting wading lesser flamingos. Caracals have a varied diet, from insects to antelope, and are renowned for the acrobatic leaps they make to snatch birds from the air. But there are few, if any, records of them hunting flamingos.


What Hollywood Is Missing About A.I.

The New Yorker

What Hollywood Is Missing About A.I. The technology is now popping up onscreen in everything from "The Morning Show" to "St. Denis Medical"--but nothing on air this year could compete with reality. Until recently, the most reliable source of clever thought experiments about ascendant technologies on television was the Netflix series "Black Mirror." The anthology drama débuted in 2011, and its creator, Charlie Brooker, quickly established his interest in the promise and perils of artificial intelligence.