PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Researchers developing AI to make the internet more accessible

‘Web agent’ navigates complex websites using language commands

2024-01-09
(Press-News.org) COLUMBUS, Ohio – In an effort to make the internet more accessible for people with disabilities, researchers at The Ohio State University have begun developing an artificial intelligence agent that could complete complex tasks on any website using simple language commands. 

In the three decades since it was first released into the public domain, the world wide web has become an incredibly intricate, dynamic system. Yet because internet function is now so integral to society’s well-being, its complexity also makes it considerably harder to navigate. 

Today there are billions of websites available to help access information or communicate with others, and many tasks on the internet can take more than a dozen steps to complete. That’s why Yu Su, co-author of the study and an assistant professor of computer science and engineering at Ohio State, said their work, which uses information taken from live sites to create web agents — online AI helpers — is a step toward making the digital world a less confusing place.

“For some people, especially those with disabilities, it’s not easy for them to browse the internet,” said Su. “We rely more and more on the computing world in our daily life and work, but there are increasingly a lot of barriers to that access, which, to some degree, widens the disparity.”

The study was presented in December at the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), a flagship conference for AI and machine learning research.

By taking advantage of the power of large language models, the agent works similarly to how humans behave when browsing the web, said Su. The Ohio State team showed that their model was able to understand the layout and functionality of different websites using only its ability to process and predict language. 

Researchers started the process by creating Mind2Web, the first dataset for generalist web agents. Though previous efforts to build web agents focused on toy simulated websites, Mind2Web fully embraces the complex and dynamic nature of real-world websites and emphasizes an agent’s ability of generalizing to entirely new websites it has never seen before. Su said that much of their success is due to their agent’s ability to handle the internet’s ever-evolving learning curve. The team lifted over 2,000 open-ended tasks from 137 different real-world websites, which they then used to train the agent. 

Some of the tasks included booking one-way and round-trip international flights, following celebrity accounts on Twitter, browsing comedy films from 1992 to 2017 streaming on Netflix, and even scheduling car knowledge tests at the DMV. Many of the tasks were very complex – for example, booking one of the international flights used in the model would take 14 actions. Such effortless versatility allows for diverse coverage on a number of websites, and opens up a new landscape for future models to explore and learn in an autonomous fashion, said Su. 

“It’s only become possible to do something like this because of the recent development of large language models like ChatGPT,” said Su. Since the chatbot became public in November 2022, millions of users have used it to automatically generate content, from poetry and jokes to cooking advice and medical diagnoses.

Still, because one website could contain thousands of raw HTML elements, it would be too costly to feed so much information to a single large language model. To address this gap, the study also introduces a framework called MindAct, a two-pronged agent that uses both small and large language models to carry out these tasks. The team found that by using this strategy, MindAct significantly outperforms other common modeling strategies and is able to understand various concepts at a decent level.

With more fine-tuning, the study points out, the model could likely be used in tandem with both open-and closed-source large language models such as Flan-T5 or GPT-4. However, their work does highlight an increasingly relevant ethical problem in creating flexible artificial intelligence, said Su. While it could certainly serve as a helpful agent to humans surfing the web, the model could also be used to enhance systems like ChatGPT and turn the entire internet into an unprecedentedly powerful tool, said Su. 

“On the one hand, we have great potential to improve our efficiency and to allow us to focus on the most creative part of our work,” he said. “But on the other hand, there’s tremendous potential for harm.” For instance, autonomous agents able to translate online steps into the real world could influence society by taking potentially dangerous actions, such as misusing financial information or spreading misinformation.

“We should be extremely cautious about these factors and make a concerted effort to try to mitigate them,” said Su. But as AI research continues to evolve, he notes that it’s likely society will experience major growth in the commercial use and performance of generalist web agents in the years to come, especially as the technology has already gained so much popularity in the public eye. 

“Throughout my career, my goal has always been trying to bridge the gap between human users and the computing world,” said Su. “That said, the real value of this tool is that it will really save people time and make the impossible possible.”

The research was supported by the National Science Foundation, the U.S. Army Research Lab and the Ohio Supercomputer Center. Other co-authors were Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang and Huan Sun, all of Ohio State.

#

Contact: Yu Su, Su.809@osu.edu  

Written by: Tatyana Woodall, Woodall.52@osu.edu

END



ELSE PRESS RELEASES FROM THIS DATE:

Scientists outline a bold solution to climate change, biodiversity loss, social injustice

2024-01-09
CORVALLIS, Ore. – An international team of scientists led by Oregon State University researchers has used a novel 500-year dataset to frame a “restorative” pathway through which humanity can avoid the worst ecological and social outcomes of climate change. In addition to charting a possible new course for society, the researchers say their “paradigm shifting” plan can support climate modeling and discussion by providing a set of actions that strongly emphasize social and economic justice as well ...

Novel chemical recycling system for vinyl polymers of cyclic styrene derivatives

Novel chemical recycling system for vinyl polymers of cyclic styrene derivatives
2024-01-09
Chemical recycling of widely used vinyl polymers (VPs) is one of the key technologies required for realizing a sustainable society. In this regard, a team of researchers from Shinshu University have recently reported a new chemical process that facilitates the depolymerization of cyclic styrene-based VPs, resulting in the recovery of a monomer precursor. This highly efficient chemical recycling system can help with effective resource circulation and the development of new plastic recycling technologies. Vinyl polymers (VPs) are ...

Quantum particles can’t separate from their properties, after all

Quantum particles can’t separate from their properties, after all
2024-01-09
The quantum Cheshire cat effect draws its name from the fictional Cheshire Cat in the Alice in Wonderland story. That cat was able to disappear, leaving only its grin behind. Similarly, in a 2013 paper, researchers claimed quantum particles are able to separate from their properties, with the properties travelling along paths the particle cannot. They named this the quantum Cheshire cat effect. Researchers since have claimed to extend this further, swapping disembodied properties between particles, disembodying multiple properties simultaneously, ...

Press passes now available for Discover BMB to be held March 23–26

2024-01-09
Complimentary press passes are now available for Discover BMB, the annual meeting of the American Society for Biochemistry and Molecular Biology (ASBMB). Join us March 23–26 in San Antonio to experience an engaging agenda showcasing the newest developments and current trends in the field. As the flagship meeting for one of the largest molecular life science organizations in the world, #DiscoverBMB brings together researchers in academia and industry from across the globe. Explore captivating science stories and connect with leading experts during the scientific symposia, which will encompass 12 themes. Topics include: Exciting ...

New CRISPR Center brings hope for rare and deadly genetic diseases

2024-01-09
Children and adults with rare, deadly genetic diseases have fresh hope for curative therapies, thanks to a new collaboration between the Innovative Genomics Institute (IGI) and Danaher Corporation, a global life sciences and diagnostics innovator.    The new Danaher-IGI Beacon for CRISPR Cures center will use genome editing to address potentially hundreds of diseases, including rare genetic disorders that have no cure. The goal is to ensure treatments can be developed and brought to patients ...

Three researchers awarded $1 million each to study new heart disease treatments, causes

2024-01-09
DALLAS, Jan. 9, 2024 — A physician-scientist from Massachusetts researching whether chemicals naturally occurring in foods could help treat heart disease, a genetics expert from Pennsylvania exploring the molecular mechanisms of lipid metabolism and cardiovascular diseases and a California-based professor of cardiovascular medicine studying how vaping impacts the development of abdominal aortic aneurysms are the most recent American Heart Association Merit Award recipients. Over the next five years, each researcher will receive a total of $1 million in funding from the Association, the world’s leading voluntary organization focused on heart and brain health and research, ...

The value of information gathering for phages

The value of information gathering for phages
2024-01-09
Phages, the viruses that infect bacteria, will pay a high growth-rate cost to access environmental information that can help them choose which lifecycle to pursue, according to a study. Yigal Meir and colleagues developed a model of a bacteria-phage system to investigate how much the viruses should be willing to invest to acquire information about their local environment. A temperate phage, once inside a bacterium, can choose one of two life cycles. In the lytic cycle, the phage turns the bacterium ...

Protecting newborns: Research lays the groundwork for a lifesaving vaccine

Protecting newborns: Research lays the groundwork for a lifesaving vaccine
2024-01-09
BINGHAMTON, N.Y. -- Researchers from Binghamton University, State University of New York are unraveling the workings of Group B Strep (GBS) infections in pregnant women, which could someday lead to a vaccine. One in five pregnant women carry Streptococcus agalactiae (Group B Strep or GBS) in the vaginal tract, which is typically harmless — except when it isn’t. The bacterial infection poses serious and even fatal consequences for newborns, including pneumonia, sepsis and meningitis, which can have long-term effects on the child’s cognitive function. Researchers ...

New study unveils machine learning-aided non-invasive imaging for rapid liver fat visualization

New study unveils machine learning-aided non-invasive imaging for rapid liver fat visualization
2024-01-09
Steatotic liver disease (SLD), previously known as non-alcoholic fatty liver disease, which includes a range of conditions caused by fat build-up in the liver due to abnormal lipid metabolism, affects about 25% of the population worldwide, making it the most common liver disorder. Often referred to as “silent liver disease,” SLD progresses without noticeable symptoms and can lead to more severe conditions like cirrhosis (liver scarring) and liver cancer. A liver biopsy—an invasive procedure involving liver tissue sample extraction from the body—is ...

Towards more accurate 3D object detection for robots and self-driving cars

Towards more accurate 3D object detection for robots and self-driving cars
2024-01-09
Robotics and autonomous vehicles are among the most rapidly growing domains in the technological landscape, with the potential to make work and transportation safer and more efficient. Since both robots and self-driving cars need to accurately perceive their surroundings, 3D object detection methods are an active area of study. Most 3D object detection methods employ LiDAR sensors to create 3D point clouds of their environment. Simply put, LiDAR sensors use laser beams to rapidly scan and measure the ...

LAST 30 PRESS RELEASES:

New register opens to crown Champion Trees across the U.S.

A unified approach to health data exchange

New superconductor with hallmark of unconventional superconductivity discovered

Global HIV study finds that cardiovascular risk models underestimate for key populations

New study offers insights into how populations conform or go against the crowd

Development of a high-performance AI device utilizing ion-controlled spin wave interference in magnetic materials

WashU researchers map individual brain dynamics

Technology for oxidizing atmospheric methane won’t help the climate

US Department of Energy announces Early Career Research Program for FY 2025

PECASE winners: 3 UVA engineering professors receive presidential early career awards

‘Turn on the lights’: DAVD display helps navy divers navigate undersea conditions

MSU researcher’s breakthrough model sheds light on solar storms and space weather

Nebraska psychology professor recognized with Presidential Early Career Award

New data shows how ‘rage giving’ boosted immigrant-serving nonprofits during the first Trump Administration

Unique characteristics of a rare liver cancer identified as clinical trial of new treatment begins

From lab to field: CABBI pipeline delivers oil-rich sorghum

Stem cell therapy jumpstarts brain recovery after stroke

Polymer editing can upcycle waste into higher-performance plastics

Research on past hurricanes aims to reduce future risk

UT Health San Antonio, UTSA researchers receive prestigious 2025 Hill Prizes for medicine and technology

Panorama of our nearest galactic neighbor unveils hundreds of millions of stars

A chain reaction: HIV vaccines can lead to antibodies against antibodies

Bacteria in polymers form cables that grow into living gels

Rotavirus protein NSP4 manipulates gastrointestinal disease severity

‘Ding-dong:’ A study finds specific neurons with an immune doorbell

A major advance in biology combines DNA and RNA and could revolutionize cancer treatments

Neutrophil elastase as a predictor of delivery in pregnant women with preterm labor

NIH to lead implementation of National Plan to End Parkinson’s Act

Growth of private equity and hospital consolidation in primary care and price implications

Online advertising of compounded glucagon-like peptide-1 receptor agonists

[Press-News.org] Researchers developing AI to make the internet more accessible
‘Web agent’ navigates complex websites using language commands