MAROKO133 Breaking ai: Scientists create ‘living plastic’ that can self-destruct itself on

📌 MAROKO133 Breaking ai: Scientists create ‘living plastic’ that can self-destruct

Researchers have developed a new type of plastic that can self-destruct on command. These materials incorporate activatable, plastic-degrading microbes alongside the polymers.

The team used two bacterial strains that worked together and completely broke down the material within just six days, without making microplastics. 

Researchers also pointed out that many microbes can break long polymeric chains into smaller pieces using enzymes. Because plastics are polymers, these enzymes or the microbes that make them could be incorporated into living plastics.  

Turning plastic durability from a problem into a programmable feature

“By embedding these microbes, plastics could effectively ‘come alive’ and self-destruct on command, turning durability from a problem into a programmable feature,” said Zhuojun Dai, a corresponding author on the paper.

“The realization that traditional plastics persist for centuries, while many applications, like packaging, are short-lived, led us to ask: Could we build degradation directly into the material’s life cycle?” 

The team also pointed out that plastics are extensively used, yet their resistance to degradation has led to severe environmental and ecological concerns. Recent advances in synthetic biology have enabled the development of spore-embedded living plastics.

Researchers stressed that living plastics can function when the spores are dormant and decay when the spores are activated. However, the degradation efficiency of individual Bacillus strain and the single-enzyme system remains limited.

Consortia-embedded living plastic

“To address this challenge, we engineered a consortia-embedded living plastic,” said researchers in the study.

“Bacillus subtilis are separately programmed with an inducible gene circuit capable of secreting two complementary plastic-degrading enzymes: Candida antarctica lipase, responsible for random-chain scission, and Burkholderia cepacia lipase, responsible for processive depolymerization and is stressed to sporulation.”

The team added that they further fabricated flexible, degradable electronic devices capable of detecting human electromyography signals using the consortia-based living plastics. Our method offers a potential strategy for tackling plastic pollution through programmed coordinated biological systems.

The team mixed the dormant spore form of B. subtilis with polycaprolactone (a polymer common in 3D printing and some surgical sutures) to protect the microbes before they were needed. 

Wearable plastic electrode

The resulting living plastic had mechanical properties similar to those of plain polycaprolactone films. However, once a nutrient broth at 122 degrees Fahrenheit (50 degrees Celsius) was added, the spores activated, breaking the plastic all the way down to its base building blocks after just six days. The cooperation between the enzymes was so efficient, it even prevented microplastic particles from being created during the degradation process, according to a press release. 

Researchers revealed that as a proof-of-concept, they created a wearable plastic electrode out of their living plastic and found it performed as expected, degrading completely within two weeks.

Researchers engineered Bacillus subtilis to produce two polymer degrading enzymes

In the future, researchers hope to develop a trigger for the spores in water, where a large portion of plastic pollution ends up. And though this work focused on just one polymer, a similar strategy could be used in other plastic types, including those commonly found in single-use plastics. 

While previous attempts relied primarily on a single enzyme So, researchers engineered Bacillus subtilis to produce two cooperative, polymer-degrading enzymes. One enzyme acts as a random chopper, snipping the long polymer chains into smaller pieces, while the other slowly chews these pieces into their monomer building units from each end.  

🔗 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

  ---