MAROKO133 Breaking ai: X-62A VISTA: World’s only self-flying F-16 advances path to autonom

📌 MAROKO133 Hot ai: X-62A VISTA: World’s only self-flying F-16 advances path to au

Lockheed Martin is using a modified F-16 fighter jet to teach artificial intelligence how to fly, maneuver, and eventually fight on its own, pushing the US Air Force closer to an era of autonomous combat aircraft.

At the center of the effort is the X-62A VISTA, a heavily modified F-16D Fighting Falcon operated at Edwards Air Force Base in California. 

Originally built in the early 1990s as a variable in-flight simulator, the aircraft was reconfigured in 2021 by Lockheed Martin’s Skunk Works and Calspan to serve as a flying testbed for autonomy and machine-learning technologies. 

The Air Force now describes the jet as an “AI pathfinder” for future fighter operations.

World’s only self-flying F-16

Though outwardly similar to a standard two-seat F-16, the VISTA is designed to behave like many different aircraft through advanced software and control systems. 

Lockheed engineers have embedded autonomy algorithms that enable onboard computers to make flight decisions that human pilots normally handle. 

Those systems can control the jet’s flight surfaces, respond to dynamic conditions, and execute complex maneuvers while a safety pilot remains onboard.

The aircraft retains the performance of a frontline fighter. Powered by a General Electric engine producing up to 28,600 pounds of thrust with afterburner, the jet can approach Mach 2 speeds and fly long-range profiles typical of operational fighters. 

Unlike combat F-16s, however, the VISTA carries no weapons and is focused entirely on testing how software can replicate, and eventually surpass, human piloting skills.

The Air Force renamed the aircraft X-62A VISTA in 2021, marking its transition from a simulation platform to an experimental autonomy testbed. In 2022, the jet flew with an artificial intelligence “agent” controlling the aircraft for extended periods, a milestone officials said marked the first time AI had actively flown a tactical jet. 

Details of those flights remain limited, reflecting the sensitive nature of the work.

Autonomous air combat

Lockheed’s efforts accelerated under the Defense Advanced Research Projects Agency’s Air Combat Evolution program, which aims to train AI to engage in air combat. 

In 2023, the VISTA flew against a human-piloted fighter in within-visual-range scenarios, with autonomy software controlling the jet’s maneuvers. 

The Air Force described those events as the first in-air tests of AI-controlled fighter combat, though it released few specifics about outcomes or tactics.

The latest upgrade announced for the VISTA underscores Lockheed’s preparations for more complex autonomous missions. 

The Air Force confirmed the jet will be fitted with Raytheon’s PhantomStrike radar, a lightweight, gallium nitride-based active electronically scanned array system. 

The radar allows aircraft to detect, track, and engage targets in the air and on the ground, a key step toward teaching AI not just how to fly, but how to sense and fight.

X-62A 

PhantomStrike is designed to be smaller, cheaper, and more power-efficient than traditional fighter radars, using an air-cooled architecture and open-system design that allows rapid upgrades. 

While the Air Force has not explained why the radar is being added now, its inclusion signals plans to test how autonomous systems manage sensors, targeting data, and tactical decision-making.

Senior US defense officials have repeatedly said that autonomy will be critical to maintaining air superiority as future conflicts demand faster decision cycles and more aircraft. 

By teaching an F-16 to fly itself, Lockheed is using a proven fighter as a bridge between today’s piloted jets and tomorrow’s autonomous air combat systems.

For now, the X-62A still flies with a human onboard. But each test flight moves the Air Force closer to a future where fighter aircraft learn, adapt, and fight with minimal human input.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Eksklusif ai: Researchers from PSU and Duke introduce “Multi-Agent Sys

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

  ---