MAROKO133 Breaking ai: Robot dives 1.5 miles to map French shipwreck with 86,000 images, r

📌 MAROKO133 Eksklusif ai: Robot dives 1.5 miles to map French shipwreck with 86,00

A remotely operated robot has retrieved artifacts from a 16th-century shipwreck more than 1.5 miles beneath the Mediterranean, offering a glimpse into how precision deep-sea robotics is transforming underwater exploration. Guided from a support vessel above, the system used camera-fed navigation and robotic pincers to maneuver across fragile debris fields, capture high-resolution imagery, and recover centuries-old objects without disturbing the surrounding site.

The mission, led by the French Navy and underwater archaeologists, centers on a wreck known as Camarat 4, discovered during a routine seabed survey. The site lies at extreme depth, where pressure, darkness, and limited access make human intervention impossible.

Operators control the robot through a tethered system, watching live video feeds as it descends for nearly an hour before reaching the seafloor. Once in position, the robot scans the wreck, hovering carefully over scattered cargo and structural remains.

According to the CBS News, the vehicle captures thousands of images while navigating tight spaces, helping researchers document the site without physically disturbing it.

At depths exceeding 1.5 miles, the robot operates under extreme pressure of nearly 150 atmospheres, where conventional equipment would fail. Its reinforced structure, stable tether system, and precision controls allow it to function reliably in near-freezing, low-light conditions.

Precision at extreme depth

“You have to be extremely precise so as not to damage the site, so as not to stir up sediment,” a French navy officer said.

That precision is critical. At such depths, even minor disturbances can obscure visibility and damage artifacts that have remained intact for centuries. The robot’s manipulators are designed to operate with minimal force, allowing it to lift fragile objects like ceramic jugs without breakage.

The system also records up to eight images per second, generating tens of thousands of visuals during a single mission. These images are later used to construct detailed 3D models of the wreck, enabling researchers to study it remotely.

“The visibility is excellent. You almost can’t tell it’s so deep,” archaeologist Franca Cibecchini said, highlighting the clarity achieved during the operation.

Mapping the unseen world

The wreck is believed to be a merchant vessel that once carried ceramics and metal cargo across Mediterranean trade routes. Archaeologists say such discoveries are rare, particularly at this depth.

“We don’t have very detailed texts about merchant ships in the 16th century, so this is a valuable source of information on maritime history,” lead archaeologist Marine Sadania said.

In addition to historical insights, the mission showcases how robotics is expanding the boundaries of exploration. The robot’s ability to revisit the site, capture data, and retrieve objects with minimal disruption marks a shift toward non-invasive underwater archaeology.

“It’s one of the deepest objects ever recovered from a wreck in France,” Sadania told AFP, referring to one of the ceramic finds brought to the surface.

As deep-sea robotics continues to evolve, such systems are expected to play a larger role not only in archaeology but also in subsea inspection, resource mapping, and environmental monitoring.

🔗 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

  ---