📌 TOPINDIATOURS Update ai: Retiring coal plants set for nuclear revival as China b

China is exploring plans to convert retiring coal-fired plants into nuclear power stations. The move targets the nation’s vast coal capacity, which is enough to power the entire United States.

Driven by decarbonisation goals and land scarcity, the “Coal to Nuclear” (C2N) strategy aims to use retiring plants’ grid and water access for compact, meltdown-proof reactors. This could offer a faster route to clean energy than building new nuclear sites.

China could be the only country capable of this. Its high-temperature gas-cooled reactors and molten salt thorium reactors generate hotter steam than ordinary reactors. That allows them to power coal-fired turbines efficiently.

Coal-to-nuclear shift

These fourth-generation reactors may also meet safety requirements more easily and gain public acceptance, researchers say. China has over 1.19 terawatts of coal-fired power, with roughly 100 gigawatts set to retire by 2030.

According to SCMP, the C2N initiative, proposed by China Energy Engineering Group Co (CEEC), provides a direct path to decarbonisation while preserving infrastructure, especially in coastal areas. It is drawing attention from policymakers, engineers, and environmental analysts amid China’s dual goals of clean energy and carbon neutrality by 2060.

Globally, coal-fired plants produce about 30% of energy-related carbon dioxide emissions. In China, coal still generates over half of electricity, making it the single largest greenhouse gas source. Nuclear power produces near-zero emissions during operation, with life-cycle emissions comparable to wind energy. China has the world’s largest number of nuclear reactors in use, under construction, or planned.

“Given China’s vast coal-fired power capacity and the long construction timeline for nuclear plants, the C2N transition could span several decades,” wrote the project team led by senior engineer Li Xiaoyu with CEEC’s China Power Engineering Consulting Group.

“During this period, if breakthroughs occur in nuclear fusion technology, the future transformation of coal plants might shift from converting them into fission reactors to repurposing them for fusion power plants,” Li added.

Leveraging advanced reactor designs

The idea is not new. The United States included provisions in the 2022 Chips and Science Act to support converting retiring coal plants to nuclear sites. TerraPower, backed by Bill Gates, plans a sodium-cooled fast reactor at a retired Wyoming coal plant.

China builds seven to eight reactors each year, far faster than the US. With its dense eastern coast, high electricity demand, and scarce land, C2N is both feasible and strategic.

Challenges remain. Traditional nuclear plants need strict safety zones and abundant water, which most inland coal plants lack. High-temperature gas-cooled reactors (HTGRs) require smaller zones, less water, and align with coal plant steam systems.

A 600-megawatt HTGR can fit on a coal site with minimal land expansion. Its safety features, like meltdown resistance without active cooling, reduce the need for emergency planning. China already operates a demonstration HTGR at Shidao Bay.

Molten salt thorium reactors, needing no water, suit inland sites. One experimental reactor runs in the Gobi Desert, with a larger electricity-generating version under construction.

Costs and public perception remain hurdles. “Social factors have become one of the key influences on infrastructure development in China. Public acceptance of nuclear energy and concerns about its safety directly affect decision-making by governments and enterprises,” Li’s team wrote.

“To scale up the transition, regulators may need to open the market to more players, including traditional power companies that own coal assets,” the studies suggest.

🔗 Sumber: interestingengineering.com

📌 TOPINDIATOURS Eksklusif ai: Researchers from PSU and Duke introduce “Multi-Agent

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

  ---