MAROKO133 Eksklusif ai: UK to convert former coal station into the nation’s first fusion p

📌 MAROKO133 Update ai: UK to convert former coal station into the nation’s first f

The UK has taken a significant step towards clean, virtually limitless energy after advancing plans to transform a former coal station into the nation’s first fusion power plant.

Once operational, the prototype plant is expected to show how fusion, which has long been considered the holy grail of energy, can be harnessed for reliable, low-carbon power generation.

It will be built at the site of the former coal-fired West Burton Power Station near Gainsborough, which was commissioned in 1966 and ran until 2023.

“We can be proud that Britain will lead the way of research, innovation and skills for a future of limitless fusion energy,” Lord Patrick Vallance, UK Minister of State for Science, Research and Innovation, said.

The move marks a turning point for the Spherical Tokamak for Energy Production (STEP) program. The world-leading project, which supports the development of a commercial fusion industry in the UK by around 2040, will now finally shift from years of research into a full delivery phase.

The global energy race

On March 16, Vallance announced the appointment of a construction partner who will accelerate the USD 266 million (GBP 200 million) revitalization of West Burton into a world-class destination for energy innovation.

The site generated electricity from coal for more than five decades before closing three years ago. Vallance also unveiled the nation’s novel Fusion Strategy, which sets out a clear roadmap for attracting private investment and building a home-grown fusion energy industry.

Both decisions come amid the Middle East conflict, which has driven up oil and gas prices. According to the government, this exposes the risks associated with long-term dependence on fossil fuel markets.

Vallance said that supporting the fusion sector will not only strengthen the UK’s energy independence, but also accelerate innovation, research, and the creation of skilled clean energy jobs for the future.

The redevelopment is expected to support up to 8,000 jobs at peak construction, with additional long-term roles in engineering, operations, and the wider supply chain. “The STEP Fusion program marks a transformational moment for our region,” Cllr Jackie Brockway, West Lindsey District Council leader, stated.

From coal to fusion

Local authorities have welcomed the project. Sally Grindrod-Smith, West Lindsey District Council planning, regeneration and communities director described it as a once-in-a-generation chance to place the region at the forefront of clean energy.

“The redevelopment of this nationally important site will create new pathways for skills, innovation and investment, while supporting our long‑term vision for economic growth and resilience,” Grindrod-Smith added.

She added that they would continue working with partners and local communities to ensure that the site delivers lasting benefits, including high-value jobs and new industry opportunities.

The program will also establish training pathways and apprenticeships to build a skilled workforce capable of supporting the emerging fusion sector. Officials said this will be critical to developing a sustainable, UK-based supply chain for future fusion power stations.

“This the moment we move from research to delivery, setting a clear path to build the UK’s prototype fusion plant at West Burton,” Paul Methven, UK Fusion Energy CEO, concluded in a press release.

The government will also invest USD 60 million (GBP 45 million) in the Sunrise AI Supercomputer. It will be used to accelerate fusion design, modelling, as well as operational planning.

🔗 Sumber: interestingengineering.com

📌 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

  ---