MAROKO133 Update ai: 1,200-year-old island found in Fiji is made of edible shellfish remai

📌 MAROKO133 Breaking ai: 1,200-year-old island found in Fiji is made of edible she

The picturesque archipelago of Fiji features a newly discovered, remarkable island entirely made up of edible shellfish.

Culasawani Island, located off the northern coast of Vanua Levu, is approximately the size of 15 tennis courts. Researchers first discovered this island in 2017; it was crabs burrowing through the earth that brought its rare but not unique contents to light, as other so-called “midden islands” exist elsewhere in the world.

Upon analyzing the island’s composition, researchers found it packed with shells rather than soil. Pacific Islanders have a long history of consuming shellfish, as explained in a recent study published in Geoarchaeology.

This history raises the possibility that Culasawani could be a “midden island,” a term used for islands composed of discarded shells. However, the absence of distinct stratigraphy and the relatively thin sedimentary layer prompted questions about this interpretation. Was Culasawani simply a “glorified landfill,” or did it form due to natural events like a tsunami?

Midden or muddle?

Once crabs alerted the researchers to the island’s distinct makeup, they collaborated with locals to determine if they had discovered a shell-dense area or an entire island comprised of shells, spanning about 3,000 square meters.

According to Popular Mechanics, midden islands—of which there are several examples across the globe—are of great academic interest because they provide critical evidence of human migration, settlement, and resource use. Researchers even uncovered pottery fragments among the shells.

Initially, they did not realize that this land was an island, as it was surrounded by mangroves and a creek, sitting at a remarkably low elevation of between 20 and 60 cm above water level at high tide. Using 20 hand augers, they drilled into the surface and found that it consisted of 70% to 90% shells.

They determined that the island is approximately 1,200 years old, suggesting that an ancient culture may have processed shellfish there. They did not find animal bones, stone tools, or evidence that humans ever permanently inhabited the island.

As the study authors described, Culasawani is situated along the north coast of Vanua Levu at the mouth of a river that provides an abundant supply of shallow-water marine shellfish. They noted other fisheries in Fiji, such as those on Viti Levu Island, where people gathered large quantities of shellfish. Culasawani might indicate just how much shellfish was once consumed.

But was Culasawani a muddle, rather than a midden island?

Probably midden

Researchers also considered whether a tsunami might have washed the shells into this area or if it impacted an ancient shell bed. Upon investigating the sedimentary layer’s thickness, they found insufficient evidence to suggest that wave action formed Culasawani. The presence of commonly consumed shellfish indicated to researchers that these deposits were not the result of wave deposition, according to Popular Mechanics.

Now, researchers plan to extend their investigations to nearby early settlement sites to determine if Culasawani is a midden or muddle. Although it remains to be proven, they suspect Culasawani is an “island of fertility,” as middens are often described, because the nutrient-rich deposits promote unique ecosystems of plant and forest growth, which hold invaluable knowledge about the cultures that once discarded their shells here.

🔗 Sumber: interestingengineering.com

📌 MAROKO133 Hot ai: Which Agent Causes Task Failures and When?Researchers from PSU

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