MAROKO133 Hot ai: James Webb Takes Long, Hard Look Inside Uranus Edisi Jam 03:47

📌 MAROKO133 Hot ai: James Webb Takes Long, Hard Look Inside Uranus Hari Ini

Uranus, the seventh planet from the Sun, has only been visited once by NASA’s Voyager 2 spacecraft, which performed a flyby of the ice giant in 1986. It came within just tens of thousands of miles of the planet’s cloud tops, where it appeared as a surprisingly “drab” light-blue orb in the blackness of space, over a billion miles from Earth.

Now, thanks to recent observations by NASA’s groundbreaking James Webb Space Telescope, we’re getting an unprecedented peek inside the layers of its upper atmosphere.

The observatory’s Near-Infrared Spectrograph (NIRSpec) instrument observed Uranus for almost a full rotation just over a year ago, showing how the planet’s ionosphere, a thin layer in the planet’s upper atmosphere that’s ionized by solar radiation, is interacting with its magnetic field.

It’s the most detailed picture of the planet’s atmosphere yet, demonstrating where auroras form on its surface. It also sheds light on the planet’s unusually tilted magnetic field. Uranus is the only planet whose equator is almost at a right angle to its orbit, an astonishing tilt of 97.77 degrees. Its magnetic axis, on the other hand, has a large tilt relative to its rotation axis, making its magnetosphere a significant outlier compared to other planets.

“This is the first time we’ve been able to see Uranus’s upper atmosphere in three dimensions,” said Northumbria University PhD student Paola Tiranti, lead author of a new paper published in the journal Geophysical Research Letters, in a statement. “With Webb’s sensitivity, we can trace how energy moves upward through the planet’s atmosphere and even see the influence of its lopsided magnetic field.”

The latest findings also support existing theories that Uranus’ upper atmosphere is still cooling, a trend that was first observed in the early 1990s, when near-infrared observations began.

Thanks to the planet’s unusual tilt, auroras act in a surprisingly different way. As on Earth, Uranian auroras are the result of charged particles from the Sun colliding with atmospheric gases, causing dancing colors to appear in the night sky. But while they’re most commonly seen around our world’s north and south poles, the situation is drastically different on Uranus.

“Uranus’s magnetosphere is one of the strangest in the Solar System,” Tiranti explained. “It’s tilted and offset from the planet’s rotation axis, which means its auroras sweep across the surface in complex ways.”

In the case of Uranus, auroras appear as glowing patches of orange and red light that extend past the edges visible in JWST observations.

“These auroral detections are hugely important because they are a direct manifestation of the planet’s internal magnetic field,” JWST interdisciplinary scientist Heidi Hammel, who was not involved in the study, told Scientific American. “We really have no other way to probing the magnetic field remotely without a spacecraft in situ.”

The findings could inform future visits to the distant ice giant. But when we’ll have a chance to get another, closer look four decades after Voyager 2’s flyby remains as uncertain as ever. Tight budgets have endangered interplanetary missions as of late, and it remains to be seen whether a trip to Uranus will still be in the cards in the coming years.

“Webb has now shown us how deeply those effects reach into the atmosphere,” Tiranti said in the statement. “By revealing Uranus’s vertical structure in such detail, Webb is helping us understand the energy balance of the ice giants. This is a crucial step towards characterising giant planets beyond our Solar System.”

More on Uranus: Scientists Say That Uranus Appears to Have a Girlfriend

The post James Webb Takes Long, Hard Look Inside Uranus appeared first on Futurism.

🔗 Sumber: futurism.com

📌 MAROKO133 Eksklusif ai: Which Agent Causes Task Failures and When?Researchers fr

Share My Research is Synced’s column that welcomes scholars to share their own research breakthroughs with over 1.5M global AI enthusiasts. Beyond technological advances, Share My Research also calls for interesting stories behind the research and exciting research ideas. Contact us: [email protected]

Meet the authors
Institutions: Penn State University, Duke University, Google DeepMind, University of Washington, Meta, Nanyang Technological University, and Oregon State University. The co-first authors are Shaokun Zhang of Penn State University and Ming Yin of Duke University.

In recent years, LLM Multi-Agent systems have garnered widespread attention for their collaborative approach to solving complex problems. However, it’s a common scenario for these systems to fail at a task despite a flurry of activity. This leaves developers with a critical question: which agent, at what point, was responsible for the failure? Sifting through vast interaction logs to pinpoint the root cause feels like finding a needle in a haystack—a time-consuming and labor-intensive effort.
 
This is a familiar frustration for developers. In increasingly complex Multi-Agent systems, failures are not only common but also incredibly difficult to diagnose due to the autonomous nature of agent collaboration and long information chains. Without a way to quickly identify the source of a failure, system iteration and optimization grind to a halt.
 
To address this challenge, researchers from Penn State University and Duke University, in collaboration with institutions including Google DeepMind, have introduced the novel research problem of “Automated Failure Attribution.” They have constructed the first benchmark dataset for this task, Who&When, and have developed and evaluated several automated attribution methods. This work not only highlights the complexity of the task but also paves a new path toward enhancing the reliability of LLM Multi-Agent systems.

The paper has been accepted as a Spotlight presentation at the top-tier machine learning conference, ICML 2025, and the code and dataset are now fully open-source.

Paper：https://arxiv.org/pdf/2505.00212
Code：https://github.com/mingyin1/Agents_Failure_Attribution
Dataset：https://huggingface.co/datasets/Kevin355/Who_and_When
 
 
Research Background and Challenges
LLM-driven Multi-Agent systems have demonstrated immense potential across many domains. However, these systems are fragile; errors by a single agent, misunderstandings between agents, or mistakes in information transmission can lead to the failure of the entire task.

Currently, when a system fails, developers are often left with manual and inefficient methods for debugging:
Manual Log Archaeology : Developers must manually review lengthy interaction logs to find the source of the problem.
Reliance on Expertise : The debugging process is highly dependent on the developer’s deep understanding of the system and the task at hand.
 
This “needle in a haystack” approach to debugging is not only inefficient but also severely hinders rapid system iteration and the improvement of system reliability. There is an urgent need for an automated, systematic method to pinpoint the cause of failures, effectively bridging the gap between “evaluation results” and “system improvement.”

Core Contributions
This paper makes several groundbreaking contributions to address the challenges above:
1. Defining a New Problem: The paper is the first to formalize “automated failure attribution” as a specific research task. This task is defined by identifying the failure-responsible agent and the decisive error step that led to the task’s failure.
2. Constructing the First Benchmark Dataset: Who&When : This dataset includes a wide range of failure logs collected from 127 LLM Multi-Agent systems, which were either algorithmically generated or hand-crafted by experts to ensure realism and diversity. Each failure log is accompanied by fine-grained human annotations for:
Who: The agent responsible for the failure.
When: The specific interaction step where the decisive error occurred.
Why: A natural language explanation of the cause of the failure.

3. Exploring Initial “Automated Attribution” Methods : Using the Who&When dataset, the paper designs and assesses three distinct methods for automated failure attribution:
– All-at-Once: This method provides the LLM with the user query and the complete failure log, asking it to identify the responsible agent and the decisive error step in a single pass. While cost-effective, it may struggle to pinpoint precise errors in long contexts.
– Step-by-Step: This approach mimics manual debugging by having the LLM review the interaction log sequentially, making a judgment at each step until the error is found. It is more precise at locating the error step but incurs higher costs and risks accumulating errors.
– Binary Search: A compromise between the first two methods, this strategy repeatedly divides the log in half, using the LLM to determine which segment contains the error. It then recursively searches the identified segment, offering a balance of cost and performance.

Experimental Results and Key Findings 
Experiments were conducted in two settings: one where the LLM knows the ground truth answer to the problem the Multi-Agent system is trying to solve (With Ground Truth) and one where it does not (Without Ground Truth). The primary model used was GPT-4o, though other models were also tested. The systematic evaluation of these methods on the Who&When dataset yielded several important insights:
– A Long Way to Go: Current methods are far from perfect. Even the best-performing single method achieved an accuracy of only about 53.5% in identifying the responsible agent and a mere 14.2% in pinpointing the exact error step. Some methods performed even worse than random guessing, underscoring the difficulty of the task.
– No “All-in-One” Solution: Different methods excel at different aspects of the problem. The All-at-Once method is better at identifying “Who,” while the Step-by-Step method is more effective at determining “When.” The Binary Search method provides a middle-ground performance.
 

– Hybrid Approaches Show Promise but at a High Cost: The researchers found that combining different methods, such as using the All-at-Once approach to identify a potential agent and then applying the Step-by-Step method to find the error, can improve overall performance. However, this comes with a significant increase in computational cost.

– State-of-the-Art Models Struggle: Surprisingly, even the most advanced reasoning models, like OpenAI o1 and DeepSeek R1, find this task challenging.- This h…

Konten dipersingkat otomatis.

🔗 Sumber: syncedreview.com