MAROKO133 Breaking ai: Researchers from PSU and Duke introduce “Multi-Agent Systems Automa

📌 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 Hot ai: Top Official Horrified When Trump Thought He Was Sending Direc

  In a baffling post last month, president Donald Trump made what appeared to be an extremely confrontational plea to his attorney general Pam Bondi. His message, addressed to “Pam” in a post on his public feed, urged the top cop to indict James Comey, the former director of the FBI.

  “Pam: I have reviewed over 30 statements and posts saying that, essentially, ‘same old story as last time, all talk, no action. Nothing is being done,’” Trump railed on Truth Social, a social media company that he owns. “We can’t delay any longer, it’s killing our reputation and credibility. They impeached me twice, and indicted me (5 times!), OVER NOTHING. JUSTICE MUST BE SERVED, NOW!!! President DJT.”

  At the time, some suspected the highly personal post was meant to be a private message which the President had bungled, instead blasting it out to the entire world. Then again, that type of fumble would be pretty extraordinary, even for Trump — would a sitting president really be conducting official businesses through his own social media app, consequences be damned?

  Luckily, the Wall Street Journal has now set the record straight. According to the paper’s sources inside the White House, the post was indeed meant for Bondi’s eyes only. One anonymous official said Trump was “surprised” when he learned it was public, because he had specifically addressed it to “Pam.”

  If that sounds too dumb to be true, remember Trump is known to be digitally illiterate, not knowing how to use a computer and once boasting that his son Barron is capable of turning on a laptop, as if that were a sign of technical acumen.

  For her part, Bondi was reportedly furious. As the WSJ writes, she quickly called White House staffers and Trump, who ended up sending a followup post an hour later saying the attorney general was doing a “GREAT job.”

  Comey, a hobbyhorse of Trump’s ever since his involvement in the infamous Steele Dossier, was indicted five days later on federal charges.

  Meanwhile, Trump’s tenuous grasp of social media continues to unravel. On Thursday, a photojournalist with the Associated Press captured a handwritten note from the visibly nervous secretary of state Marco Rubio, instructing the president to make a social media post.

  “You need to approve a Truth Social post soon so you can announce deal first,” the note read, referencing the Israel-Hamas Peace Plan.

  About ten minutes later, the president made his awkward exit.

  “I have to go now to try and solve some problems in the Middle East — although I’m very well represented by our secretary of state,” Trump told the right-wing influencers he was meeting with. “He could probably do an even better job than me, but who knows.”

  More on Trump: Trump’s $175 Billion Golden Dome is Turning Into a Disaster

  The post Top Official Horrified When Trump Thought He Was Sending Direct Message But Accidentally Posted It on Main Account appeared first on Futurism.

  🔗 Sumber: futurism.com

  ---