📌 TOPINDIATOURS Breaking ai: Pentagon taps six vendors to build highly maneuverabl

The Pentagon is intensifying its pursuit of Mach 5+ flight through a new $68 million initiative.

The Joint Hypersonics Transition Office (JHTO) recently awarded contracts to six non-traditional vendors.

These agreements aim to solve the engineering hurdles that currently stall high-speed weapon development.

Partnering with the Naval Surface Warfare Center (NSWC) Crane Division, the JHTO selected Leidos, GoHypersonic, and Kratos.

The Purdue Applied Research Institute, Halo Engines, and Special Aerospace Services also secured spots.

These firms will develop next-generation capabilities under Other Transaction Agreements (OTAs).

Building agile Mach 5+ systems

The selected vendors will focus on making Mach 5+ hypersonic missiles more than just fast. They must ensure these systems remain maneuverable during flight.

Engineers will work on improved aerodynamics and propulsion designs.

This work includes better mission planning and overall effectiveness.

Existing programs often struggle with the extreme physics of hypersonic flight. Friction at five times the speed of sound generates immense heat.

This environment can destroy standard airframes and disrupt electronics.

The new contracts prioritize “science-and-technology” (S&T) advancements to overcome these barriers.

“Through these [science-and-technology] priorities, the awarded organizations will develop and demonstrate new subsystem technologies, strengthen the scientific foundations behind hypersonics and explore emerging technologies with the potential to transform future systems,” an NSTXL press release stated.

Testing through digital simulation

The JHTO wants results quickly. The program has a three-year performance period. Each project will mature through rigorous modeling and simulation.

This digital-first approach helps the Pentagon bypass the current lack of physical testing infrastructure in the United States.

“Each award will mature through modeling and simulation, and relevant ground or flight experimentation,” the NSTXL release continued.

Advanced computer models allow engineers to predict how Mach 5+ hypersonic missiles behave. They can test airflows and extreme thermal loads without expensive flight failures.

These simulations provide critical data on in-flight maneuverability. The ultimate goal is a flight-ready prototype before the contract ends.

The National Security Technology Accelerator (NSTXL) manages these contracts through the S2MARTS mechanism.

This non-profit acts as a bridge between the government and private tech firms. It helps move innovative technologies into the hands of American warfighters.

This collaboration allows smaller, specialized companies to contribute to major defense projects.

Hypersonic weapons are a top priority for the Department of Defense. These missiles maneuver through the atmosphere to hit targets.

Their speed and agility make them difficult for enemy defenses to detect or defeat.

However, designing them remains a massive engineering challenge for even the largest aerospace firms.

The Pentagon established the JHTO in 2020 to solve these specific problems. By partnering with NSWC Crane, the office creates new development strategies.

These new awards represent a major shift toward agile, non-traditional aerospace manufacturing.

If successful, these six companies could provide the breakthrough the U.S. military needs to stay ahead.

🔗 Sumber: interestingengineering.com

📌 TOPINDIATOURS Eksklusif ai: Which Agent Causes Task Failures and When?Researcher

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: chain.zhang@jiqizhixin.com

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