📌 TOPINDIATOURS Hot ai: US military laser tests and suspected cartel drones trigge

On the night of Tuesday, the Federal Aviation Administration (FAA) surprised pilots with a notice that airspace over El Paso, Texas, would be closed for 10 days due to “special security reasons.”

By Wednesday morning, the restrictions were suddenly lifted, leaving the city’s airport in confusion for several hours.

The abrupt decision raised questions across federal agencies and drew attention from lawmakers and international observers. Officials gave conflicting explanations for the closure, leaving the public unsure about what actually occurred in the skies above El Paso.

Conflicting explanations from officials

Trump administration officials, including Transportation Secretary Sean Duffy, claimed the airspace closure was prompted by drones operated by Mexican drug cartels crossing into the United States. Duffy posted on social media that the FAA and Department of Defense “acted swiftly” and had “neutralised” the threat.

However, other sources familiar with the situation said the closure was related to military testing, not cartel drones. The Pentagon reportedly flew drones and tested high-energy laser technology designed to counter unmanned aircraft.

These activities, conducted outside normal flight paths near El Paso International Airport, caused FAA concern about possible interference with civilian flights.

The Pentagon recently used the technology to shoot down an object it thought was a drone, which turned out to be a party balloon, according to The Wall Street Journal.

Lawmakers demand clarity

The unusual closure quickly drew attention from both Republican and Democratic lawmakers. Senator Ted Cruz of Texas, who chairs the Senate Commerce Committee, said, “The details of what exactly occurred over El Paso are unclear,” and requested a classified briefing.

FAA Administrator Bryan Bedford briefed senators on air traffic modernization but declined to discuss El Paso further.

Democrats also criticized the move. Congressman Rick Larsen and André Carson called the situation “unacceptable” and said expanded Defense Department authorities allowed the Pentagon “to act recklessly in the public airspace.”

Mexico’s President Claudia Sheinbaum announced her government would investigate the closure, stating, “There is no information about the use of drones at the border.”

Local officials were caught off guard. Chris Canales, a member of El Paso’s city council, said, “We have no reason to believe that there is any kind of imminent safety threat to El Paso, but we still have no reason for the flight restriction provided by the FAA or any federal authority.”

Military counter-drone efforts

The closure highlights the growing concern over drone threats from criminal organizations. Senior Homeland Security officials told lawmakers last year that Mexican drug cartels were using weaponized drones against each other and could target U.S. forces.

President Donald Trump has repeatedly vowed to combat these cartels, and authorities are exploring measures to intercept or neutralize illicit drone operations.

The U.S. Army has invested in directed-energy weapons, including high-energy lasers, as a flexible, low-cost alternative to missiles for counter-drone operations. FAA and Defense Department officials had planned a meeting on February 20 to discuss the safety impacts of these technologies, but military priorities may have accelerated testing.

The El Paso incident underscores the challenges of coordinating military technology testing with civilian airspace safety, especially near international borders. It also raises questions about communication between federal agencies and local authorities when rapid action is taken in the skies over U.S. cities.

🔗 Sumber: interestingengineering.com

📌 TOPINDIATOURS Hot ai: Researchers from PSU and Duke introduce “Multi-Agent Syste

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

  ---