MAROKO133 Breaking ai: Scientist Says Galaxies Shining With Radio Signals Could Indicate N

📌 MAROKO133 Eksklusif ai: Scientist Says Galaxies Shining With Radio Signals Could

The Fermi Paradox, first devised by physicist Enrico Fermi in the 1950s, asks why we haven’t detected alien civilization yet, despite the vast universe teeming with countless potentially habitable planets.

While many theories have been put forward in response to the paradox, many experts believe that it’s only a matter of time until we can detect alien signals. In fact, as Breakthrough Listen Initiative astronomer Brian Lacki suggests, the universe could be teeming with billions of extraterrestrial intelligences (ETIs) — and, in a striking claim, all that activity just might explain “radio bright” active galaxies that emit powerful radio emissions across vast distances.

In a series of three yet-to-be-peer-reviewed papers, first spotted by Universe Today, Lacki raised the possibility that galaxies “blazing with technosignatures” could suggest the existence of a “large number” of “different metasocieties” sending broadcasts across the radio spectrum.

Basically, the idea is that alien civilizations might be rare — but that once one has attained a certain level of technological capability, it’s likely to expand or seed elsewhere within its galaxy.

“If interstellar travel and migration are indeed possible, then ETIs are unlike known astrophysical phenomena in that they can reproduce,” he wrote in his first paper. “Replication can amplify quirks of history onto galactic scales.”

“Thus, supposing that starfaring ETIs are rare, one galaxy could have no ETIs while another, astrophysically indistinguishable, could have billions of inhabited worlds,” he added. “This motivates the use of a probabilistic treatment of the observable technosignatures of galaxies, wherein different galaxies can have wildly different broadcast distributions.”

In one of the papers, Lacki suggests that placing “constraints on radio broadcasts from entire populations of inhabited galaxies” instead of focusing on efforts to observe individual star-bound civilizations.

“If you have some subset that has a lot of radio transmissions, they will appear radio-bright,” he told Universe Today. “Since we know basically how many galaxies there are at each level of flux, we can set upper limits on how many of these ‘artificial radio galaxies’ there are.”

Lacki suggests detecting the combined glow of the emissions of several civilizations. It’s an approach that comes with its own challenges, as separating technological signatures from other natural sources of radio transmissions, like supermassive black holes at the center of galaxies, could prove difficult.

“The trouble is that you can’t tell whether that emission is natural or artificial just from knowing how bright it is in the radio,” Lacki told Universe Today, noting that “we expect it is natural in almost all, if not all, cases.”

Of course, probing distant galaxies for radio signatures is only one tiny piece of a much greater puzzle, and just one method among many. For instance, we could identify star systems that give off huge amounts of infrared emissions with the hopes of spotting a Dyson sphere, a hypothetical megastructure an alien civilization could build around a star or black hole to capture most of its power.

Or we could probe the skies for civilizations emitting gamma rays or X-rays.

Regardless of our approach, having a robust framework to know where to look seems like a wise first step to take in our effort to figure out if we’re alone in the universe or not.

More on aliens: Mysterious Object Cruising Through Solar System May Have Emitted a Signal, Scientist Says

The post Scientist Says Galaxies Shining With Radio Signals Could Indicate Numerous Advanced Civilizations appeared first on Futurism.

🔗 Sumber: futurism.com

📌 MAROKO133 Breaking ai: Researchers from PSU and Duke introduce “Multi-Agent Syst

Share My Research is Synced’s column that welcomes scholars to share their own research breakthroughs with over 2M global AI enthusiasts. Beyond technological advances, Share My Research also calls for interesting stories behind the research and exciting research ideas. 

Meet the author
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

2. failure-responsible agent and the decisive error step that led to the task’s failure.

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 m…

  Konten dipersingkat otomatis.

  🔗 Sumber: syncedreview.com

  ---