MAROKO133 Update ai: Researchers from PSU and Duke introduce “Multi-Agent Systems Automate

📌 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

  ---

  📌 MAROKO133 Eksklusif ai: New battery recharges using sunlight, releases hydrogen

  A new copolymer-based battery developed by researchers at Ulm and Jena universities in Germany stores energy from sunlight for days and can release it when required as green hydrogen. The battery is rechargeable, and the charge and discharge process can be activated by flipping a pH switch, a press release said. 

  With the focus on switching away from fossil fuels, countries are adopting large-scale solar and wind power plants. However, for applications requiring higher energy density, hydrogen is a more viable alternative. It can be burnt, much like a fossil fuel, but produces only water as a byproduct, offering a carbon-free solution for energy-intensive applications. 

  However, hydrogen production itself can be a carbon-emitting process. Large-scale hydrogen plants use methane reforming to produce hydrogen, since it is cost-effective. For hydrogen to be an ideal replacement for fossil fuels, it must be produced using solar or wind energy, also known as green hydrogen. 

  Copolymer to the rescue

  Green hydrogen can be produced using sunlight through a photocatalytic process. Once the gas is produced, it needs to be stored separately in tanks and processed when required. However, a research team led by Ulrich Schubert at Jena University and Sven Rau at Ulm University decided to use copolymer molecules instead. 

  Copolymers are macromolecules that consist of different organic building blocks. They have a stable framework and can be equipped with specific functional units. For this solar battery, the researchers used a water-soluble copolymer with reinforced redox activity as its chief functional unit. 

  When exposed to sunlight, the system achieves 80% charging efficiency. Once charged, the system can maintain its charged state for several days. To retrieve the energy, the researchers added an acid and a hydrogen-evolution catalyst to cause the electrons stored in the system to combine with protons, thereby releasing hydrogen. Here, the system’s efficiency is high again, reaching 72 percent. 

  Uses pH as a switch

  The copolymer-based system features redox reactions that are completely reversible. So, when the battery is discharged, it can be left in the Sun to recharge, facilitating multiple catalytic and storage cycles. 

  To reset the system, the researchers simply change its pH value. But pH is not just a switch; it is also an indicator of the polymer’s state of charge. When discharged, the presence of the acid changes the colour from violet to yellow. 

  When placed in sunlight to charge, the system changes colour from yellow to violet again, showing that the battery has a charge it can release as hydrogen when necessary. The hydrogen released could be used for a wide variety of applications, from running electric cars to manufacturing steel or generating clean electricity on demand.

  “The project is also of scientific significance because it combines very different concepts from the field of chemistry that otherwise have few points of contact: namely, macromolecular polymer chemistry and photocatalysis,” added Rau in the press release. 

  “The results open up new perspectives for cost-effective, scalable solar storage technologies – and provide an important building block on the way to a sustainable, chemical-based energy economy,” concluded Schubert. 

  The research findings were published in the journal Nature Communications. 

  🔗 Sumber: interestingengineering.com

  ---