MAROKO133 Breaking ai: Which Agent Causes Task Failures and When?Researchers from PSU and

📌 MAROKO133 Eksklusif ai: Which Agent Causes Task Failures and When?Researchers fr

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: [email protected]

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

📌 MAROKO133 Update ai: Grok Is Being Used to Depict Horrific Violence Against Real

Earlier this week, a troubling trend emerged on X-formerly-Twitter as people started asking Elon Musk’s chatbot Grok to unclothe images of real people. This resulted in a wave of nonconsensual pornographic images flooding the largely unmoderated social media site, with some of the sexualized images even depicting minors.

In addition to the sexual imagery of underage girls, the women depicted in Grok-generated nonconsensual porn range from some who appear to be private citizens to a slew of celebrities, from famous actresses to the First Lady of the United States. And somehow, that was only the tip of the iceberg.

When we dug through this content, we noticed another stomach-churning variation of the trend: Grok, at the request of users, altering images to depict real women being sexually abused, humiliated, hurt, and even killed.

Much of this material was directed at online models and sex workers, who already face a disproportionately high risk of violence and homicide.

One of the disturbing Grok-generated images we reviewed depicted a widely-followed model restrained in the trunk of a vehicle, sitting on a blue tarp next to shovel — insinuating that she was on her way to being murdered.

Other AI images involved people specifically asking Grok to put women in scenarios where they were obviously being assaulted, which was made clear by users requesting that the chatbot make the women “look scared.” Some users asked for humiliating phrases to be written on women’s bodies, while others asked Grok to give women visible injuries like black eyes and bruises. Many Grok-generated images involved women being put into restraints against their will. At least one user asked Grok to create incestuous pornography, to which the chatbot readily complied.

That a social media-infused chatbot could so readily transform into a nonconsensual porn machine to create unwanted and even violent images of real women at scale is, on its face, deeply unsettling. Even worse was that the creators of these images often seemed to be treating the action like a game or meme, with an air of laughter and detachment.

That nonchalance may speak to a normalization of this kind of nonconsensual content, which before had largely been relegated to darker corners if the internet. Women and girls, meanwhile, continue to face the real-world harm wrought by nonconsensual deepfakes, which are easier than ever to generate thanks to AI-powered “nudify” tools — and, apparently, multibillion-dollar chatbots.

We’ve reached out to xAI for comment, but haven’t received any reply.

But yesterday, Musk, who owns both X and xAI, took to the social media platform to ask netizens to “please help us make Grok as perfect as possible.”

“Your support,” he added, “is much appreciated.”

More on Grok and safety: Elon Musk’s Grok Is Providing Extremely Detailed and Creepy Instructions for Stalking

The post Grok Is Being Used to Depict Horrific Violence Against Real Women appeared first on Futurism.

🔗 Sumber: futurism.com