MAROKO133 Eksklusif ai: Researchers from PSU and Duke introduce “Multi-Agent Systems Autom

📌 MAROKO133 Hot ai: Researchers from PSU and Duke introduce “Multi-Agent Systems A

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

  ---

  📌 MAROKO133 Hot ai: Breakthrough propulsion system lets satellites use Earth’s atm

  A significant step in satellite propulsion is paving the way for a new era in space technology. The new efforts in air-breathing electric propulsion (ABEP) systems promise to revolutionize how satellites operate—especially in extremely low Earth orbits.

  Conventional satellites rely on onboard fuel to maintain their orbit and perform maneuvers. However, this approach comes with limitations: fuel adds weight, restricts mission duration, and increases costs. Over time, satellites lose altitude due to atmospheric drag and must expend fuel to stay in orbit.

  Innovation allows satellites to operate sustainably at very low altitudes

  The newly developed air-breathing electric propulsion (ABEP) system challenges this model by eliminating the need for traditional propellant. Instead, it collects and uses residual atmospheric particles as fuel. This innovation allows satellites to operate sustainably at very low altitudes, known as Very Low Earth Orbit (VLEO).

  At altitudes between roughly 180 and 250 kilometers, traces of atmospheric gases are still present. The ABEP system captures these particles, ionizes them, and accelerates them to generate thrust.

  This process offers major advantages including no onboard fuel requirement, reducing launch mass and virtually unlimited propulsion, as long as atmospheric particles are available.

  System passed a key design review

  The system has recently passed a key design review, confirming both its technical feasibility and readiness for further development.

  The project “Cathodeless Electric Propulsion Thruster for Air-Breathing Electric Propulsion Systems” is carried out by TransMIT GmbH.

  IQM is leading the development of a cathodeless electric propulsion (EP) thruster under ESA funding, aimed at removing the need for external neutralisers in atmosphere-breathing systems. The goal is to design, manufacture, and test a prototype thruster capable of stable operation with Earth’s atmospheric gases (N₂/O₂ mixtures), achieving at least 50% electrical efficiency and a minimum specific impulse of 4200 s.

  This activity builds on feasibility studies and technology trade-offs carried out at IQM, which identified the most promising concepts for cathodeless EP operation in reactive, oxygen-rich environments. A prototype is now under construction, with testing planned in vacuum facilities capable of reproducing Very Low Earth Orbit (VLEO) conditions.

  The propulsion system integrates the most promising solutions for this specific target: a traditional high-frequency ion thruster with unique cathodeless functional characteristics, eliminating the need for a cathode assembly, which, while a critical component for ion thruster operation, has proven difficult to implement in the ABEP concept, according to a report.

  This achievement represents a significant milestone in European efforts to develop next-generation propulsion systems that will enable sustainable satellite constellations in extremely low orbits by using particles from the atmosphere as fuel for the engine to compensate for the drag that these very particles exert on the satellite.

  Air-breathing propulsion

  The adoption of air-breathing propulsion could significantly reshape the satellite industry. With longer mission lifespans and reduced dependency on fuel, satellite operators can lower costs and improve efficiency.

  While still under development, air-breathing propulsion represents a major leap toward sustainable and efficient space operations. As testing progresses and the technology matures, it may soon enable a new class of satellites capable of operating closer to Earth than ever before.

  In essence, this innovation marks not just an incremental improvement—but a fundamental shift in how we think about propulsion in space.

  🔗 Sumber: interestingengineering.com

  ---