MAROKO133 Update ai: Cosmic mystery deepens as astronomers uncover most distant, powerful

📌 MAROKO133 Update ai: Cosmic mystery deepens as astronomers uncover most distant,

A giant cosmic mystery just got bigger.

Astronomers have spotted the most distant and most powerful “odd radio circle” (ORC) ever recorded, deepening the puzzle of these rare celestial rings.

ORCs were first identified only six years ago, and so far, just a few have been confirmed. They are enormous, faint, ring-shaped structures of radio emission, often stretching 10–20 times the size of our Milky Way.

Unlike ordinary galaxies, they glow only in radio light, produced by relativistic, magnetised plasma.

Earlier theories suggested ORCs might form from shockwaves unleashed when supermassive black holes or galaxies collide. But a new study points in a different direction, linking them instead to superwind outflows from spiral host galaxies.

Citizen science breakthrough

The discovery was made by researchers from the University of Mumbai using the RAD@home Astronomy Collaboratory citizen science platform, alongside the Low-Frequency Array (LOFAR), the world’s largest radio telescope at low frequencies.

The newly identified source, RAD J131346.9+500320, sits at a redshift of ~0.94—when the universe was only half its current age.

That makes it both the farthest and most powerful ORC known so far. Adding to the intrigue, it contains two intersecting rings, only the second such case ever found.

Dr Ananda Hota, founder of RAD@home, said: “This work shows how professional astronomers and citizen scientists together can push the boundaries of scientific discovery. ORCs are among the most bizarre and beautiful cosmic structures we’ve ever seen – and they may hold vital clues about how galaxies and black holes co-evolve, hand-in-hand.”

RAD J131346.9+500320 is also the first ORC discovered by citizen scientists and the first identified with LOFAR.

Colossal cosmic structures

Alongside this record-breaking ORC, two other cosmic giants were uncovered. One, RAD J122622.6+640622, spans nearly three million light-years—25 times the Milky Way’s size.

Its jet bends sharply, blasting a huge radio ring about 100,000 light-years wide. The second, RAD J142004.0+621715, stretches across 1.4 million light-years and also forms a striking radio ring at the end of one of its jets.

Both lie within crowded galaxy clusters, where their jets likely interact with million-degree hot plasma, sculpting these unusual shapes. All three new objects sit in clusters weighing about 100 trillion Suns, hinting that black hole jets colliding with dense cosmic environments may be central to their formation.

Co-author Dr Pratik Dabhade, of the National Centre for Nuclear Research in Warsaw, said: “These discoveries show that ORCs and radio rings are not isolated curiosities – they are part of a broader family of exotic plasma structures shaped by black hole jets, winds, and their environments. The fact that citizen scientists uncovered them highlights the continued importance of human pattern recognition, even in the age of machine learning.”

Future telescopes such as the Square Kilometre Array are expected to reveal many more ORCs. Combined with surveys like DESI and the Rubin Observatory’s LSST, astronomers hope to finally trace how these strange rings emerge and evolve.

For now, the latest discoveries represent a major leap forward, led not by machines but by human curiosity. The findings of the study have been published in Monthly Notices of the Royal Astronomical Society.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Breaking ai: Which Agent Causes Task Failures and When?Researchers fro

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