MAROKO133 Update ai: Iran Says It’s Ready to Destroy the Global Economy Edisi Jam 04:17

📌 MAROKO133 Hot ai: Iran Says It’s Ready to Destroy the Global Economy Hari Ini

If the Trump administration was expecting it’d quickly wrap up its “little excursion” in Iran like in a repeat of Venezuela, geopolitical reality had different ideas. 

On Wednesday, the Iranian government said it was ready for a long war that would “destroy” the global economy, Le Monde reported, as it continues to shut down a key passageway for oil supplies, the Strait of Hormuz.

“Get ready for the oil barrel to be at $200 because the oil price depends on the regional stability which you have destabilised,” Ebrahim Zolfaqari, a spokesperson for the Islamic Revolutionary Guard Corps, told Reuters.

Oil prices have surged since February 28, when the US and Israel opened aggressions by assassinating Iran’s supreme leader Ali Khamenei in a series of missile strikes that also killed the commander of the IRGC, the minister of defense, and other top brass. The strikes have also killed more than 1,000 civilians. One US Tomahawk missile struck an elementary school, killing at least 175 people including numerous students in a massacre that’s now under investigation by the Pentagon.

The regime has not collapsed, as some Trump officials may have hoped, and it retaliated by launching its own campaign of missile and drone strikes across US allies in the Middle East.

The IRGC has vowed that not a “single liter of oil” would pass through the Strait of Hormuz to hostile nations. Approximately 20 percent of the world’s global oil supplies flow through the passage, where Iran has cut off shipping traffic for the past two weeks. The strait connects the Persian Gulf to the Gulf of Oman, providing the only route to the open ocean for supertankers carrying oil from Saudi Arabia, Kuwait, Qatar, the UAE, Iran, and others.

Two oil vessels were struck with explosions in an Iraqi port on Thursday, in suspected Iranian attacks. Three other cargo ships were also struck and set ablaze in the Gulf hours before. The IRGC has claimed responsibility for at least one of those attacks, a Thai bulk carrier.

Whether the gravity of the situation has sunk in for US leadership is an open question. The day before the seeming escalations in the Gulf, Donald Trump declared that the US had already won the war.

Iran’s newly appointed supreme leader Mojtaba Khamenei redoubled pressure on oil markets Thursday. In his first public message since being appointed mere days ago, Khamenei affirmed that the Strait of Hormuz should remain closed, adding his demand that all US bases in the region should be closed, per Reuters.

Last week, Brent crude oil prices reached over $100 per barrel for the first time since 2022, peaking at nearly $120 per barrel on Monday, sending shudders throughout the economy. Gas prices in the US have surged to an average of over $3.50 per gallon, according to AAA, and are already soaring far past that point on the West Coast.

The International Energy Agency said the ongoing war has caused the largest disruption to global oil supplies in history. On Wednesday, it announced that member countries would release 400 million barrels of oil from emergency stockpiles, itself a historic figure, to dampen surging oil prices. The US said it would chip in with 172 million barrels from its ​Strategic Petroleum Reserve. Despite the announcement, Brent crude rose more than 8 percent to over $100 per barrel overnight, Axios reported.

President Trump was transparent that the strain on oil markets would provide a windfall for US producers.

“The United States is the largest Oil Producer in the World, by far, so when oil prices go up, we make a lot of money,” he wrote in a post on Truth Social, his social media site.

More on Iran: Toxic Sludge Raining Down on Iran After Bombing of Oil Facilities

The post Iran Says It’s Ready to Destroy the Global Economy appeared first on Futurism.

🔗 Sumber: futurism.com

📌 MAROKO133 Update ai: Which Agent Causes Task Failures and When?Researchers from

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