MAROKO133 Eksklusif ai: Programmable soft materials unlock asymmetric motion for next-gen

📌 MAROKO133 Hot ai: Programmable soft materials unlock asymmetric motion for next-

A new class of soft, programmable composites that can twist, stiffen, and move differently depending on direction may soon redefine how robots sense and act in the world.

A research team at The Hong Kong University of Science and Technology (HKUST) has engineered soft materials with highly tunable, asymmetric mechanical responses, an ability crucial for next-generation mechano-intelligent systems.

The breakthrough integrates “shear-jamming transitions” into compliant polymeric solids, allowing the materials to stiffen dramatically under shear while remaining flexible otherwise.

This design enables soft structures that behave differently when pushed, pulled, or twisted from different directions.

It’s a shift away from traditional metamaterials, which often rely on rigid frameworks that fracture easily. In contrast, these shear-jammed soft composites deliver programmable, defect-tolerant performance without the fragility of conventional designs.

Directional intelligence emerges

In fields like soft robotics, synthetic tissues, and flexible electronics, materials that respond differently depending on the direction of force are key to achieving intelligent behavior. But so far, engineers have mostly relied on complex structures that break easily or fail under stress.

The HKUST team’s approach offers a simpler, more robust path. Their materials can be tuned across multiple scales by controlling how and when the internal particles transition into a shear-jammed state.

This allows directional behaviors, shape-memory asymmetry, and strain-dependent stiffness all within the same soft solid.

“These soft composites are highly programmable and remarkably fracture-resistant,” the researchers noted. They added that the mechanical properties “can be tailored across multiple scales through the shear-jamming phase transition.”

The team also demonstrated how these materials can be combined with spatially modulated magnetic profiles to create “active soft solids” capable of directional motion.

Soft robots advance

These magnetically guided structures behave like bio-inspired robots, capable of navigating confined environments where conventional robots would stall.

They also function as selective flow-control valves in microfluidic systems, opening cracks for the development of soft pumps, biomedical devices, and adaptive medical tools.

The researchers emphasize that the work bridges granular physics and polymer science, bringing two fields together to craft a new generation of non-reciprocal soft materials.

This convergence enables soft structures that can sense, adapt, and respond with mechanical intelligence rather than relying on electronics alone.

From an engineering standpoint, the results suggest a new design platform for creating directionally sensitive, energy-efficient materials that can interact intelligently with their surroundings.

Such materials could form the backbone of future soft machines and shape-changing devices.

The interdisciplinary project brought together researchers from HKUST’s Departments of Physics (PHYS) and Mechanical and Aerospace Engineering (MAE). XU Chang, a PhD student in PHYS, is the paper’s first author.

The study was supported by the Hong Kong Research Grants Council and the HKUST Marine Robotics and Blue Economy Technology Grant. The findings were published in Nature Materials.

🔗 Sumber: interestingengineering.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