MAROKO133 Breaking ai: Rivian gives its old EV batteries new life in 10 MWh factory storag

📌 MAROKO133 Update ai: Rivian gives its old EV batteries new life in 10 MWh factor

Rivian, an electric vehicle maker, and battery recycling and materials company Redwood Materials will deploy a 10 megawatt-hour second-life battery energy storage system at Rivian’s manufacturing facility in Normal, Illinois, using more than 100 repurposed electric vehicle battery packs to cut energy costs and support grid stability during peak demand.

The system will take used Rivian EV battery packs and convert them into a stationary energy storage unit on-site at the factory.

Redwood Materials will integrate the packs into its Redwood Energy system, using its Pack Manager technology to control and dispatch stored electricity when needed. The setup is designed to reduce peak electricity costs and ease strain on the local grid.

The initial deployment will provide 10 MWh of dispatchable energy. The companies say the model is designed to be scalable and can be expanded as more second-life battery packs become available.

The focus is on turning retired EV batteries into a distributed energy resource for industrial use rather than sending them directly to recycling.

Rivian said the approach extends the useful life of its batteries beyond vehicle use and turns them into grid-supporting assets.

Redwood Materials will handle system integration and energy management, positioning the setup as a flexible storage solution for manufacturing sites with high and variable electricity demand.

Batteries beyond vehicle life

Electricity demand in the U.S. is rising faster than grid expansion, creating pressure on industrial users who face higher peak energy costs.

Large-scale storage systems are increasingly seen as a way to balance demand without waiting years for new transmission infrastructure.

The companies argue that second-life EV batteries offer a faster route to add storage capacity. Instead of manufacturing new stationary batteries, they reuse existing EV packs that still retain usable capacity after vehicle retirement.

This reduces costs and shortens deployment timelines for industrial energy storage.

“EVs represent a massive, distributed and highly competitive energy resource,” said Rivian Founder and CEO RJ Scaringe.

“As energy needs grow, our grid needs to be flexible, secure, and affordable. Our partnership with Redwood enables us to utilize our vehicle’s batteries beyond the life of a vehicle and contribute to grid health and American competitiveness.”

Grid load shifting strategy

Redwood Materials said electricity demand growth is becoming a constraint for industrial expansion and that existing battery assets in the U.S. represent a large untapped energy storage base.

The company is positioning second-life batteries as a near-term solution to expand grid capacity without waiting for new manufacturing or infrastructure buildouts.

“Electricity demand is accelerating faster than the grid can expand, posing a constraint on industrial growth,” said JB Straubel, Redwood Materials Founder and CEO.

“At the same time, the massive amount of domestic battery assets already in the U.S. market represents a strategic energy resource. Our partnership with Rivian shows how EV battery packs can be turned into dispatchable energy resources, bringing new capacity online quickly, supporting critical manufacturing, and reducing strain on the grid without waiting years for new infrastructure. This is a scalable model for how we add meaningful energy capacity in the near term.”

The system is intended to support peak shaving, where stored energy is released during high-demand periods such as heat waves. This reduces the need for expensive peak electricity purchases and lowers stress on the grid while maintaining stable factory operations.

Redwood said its battery integration platform is designed to scale as more EV packs become available across the U.S. fleet, turning retired mobility batteries into a distributed storage network for industrial and grid use.

The deployment marks one of the early industrial-scale uses of second-life EV batteries directly at a manufacturing site, combining energy storage, cost reduction, and grid support in a single system.

🔗 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

  ---