📌 TOPINDIATOURS Breaking ai: 12,000-year-old case of rare genetic disease confirme

Researchers identified the earliest case of a genetic disease with the help of DNA: a mother and child buried together in southern Italy 12,000 years ago both exhibited signs of possessing a rare genetic disease, highlighting the deep history of this medical phenomenon throughout human history.

Just published in The New England Journal of Medicine, scientists examined the remains of two Stone Age skeletons discovered in 1963. This Upper Paleolithic burial even became famous, though puzzling to researchers, because the unusual skeletal remains were even disfigured.

An adolescent, Romito 2, was laid to rest in the arms of Romito 1, believed to be an adult female. Their embrace led archaeologists to infer that they were mother and child. The younger, at 3.6 feet, exhibited signs of having acromesomelic dysplasia, a condition marked by severe short stature and pronounced limb shortening. The mother, or Romito 1, showed similarities, though not as pronounced as her younger relative.

Archaeologists couldn’t prove it though. Not until now.

A seriously important moment for rare diseases

According to a press release, a team of researchers from the University of Vienna and collaborators in Italy, Portugal, and Belgium employed an interdisciplinary approach, combining paleogenomics, clinical genetics, and physical anthropology.

They first extracted DNA from the petrous part of the temporal bone of both individuals, a region known for preserving genetic material. These two individuals had a first-degree relationship, they confirmed, so they appeared to have been mother and child.

A real breakthrough for medical science

Then, after screening the genes associated with skeletal growth and comparing the ancient and modern data, researchers diagnosed her with acromesomelic dysplasia. She had a homozyhous variant of the NPR2 gene, essential for bone growth. Her mother, most likely, Romito 1, carried an altered copy of the same gene, which explained her shorter stature, though her daughter appeared to suffer from a more acute case of the condition.

Co-author Adrian Daly told Live Science in an email that “this is the earliest DNA confirmed genetic diagnosis ever made in humans, the earliest diagnosis of a rare disease, and the earliest familial genetic case; it is a real breakthrough for medical science.”

“Identifying with near certainty a single base change in a gene in a person that died between 12,000 and 13,000 years ago is the earliest such diagnosis by about 10 millennia.”

Ron Pinhasi from the University of Vienna spoke further of the significance of the study in a press release as they applied ancient DNA analysis “to specific mutations in prehistoric individuals.” The methodology employed helps to trace just how far back genetic conditions travel through our human history to even glean new insights into unknown variants.

“Rare genetic diseases are not a modern phenomenon but have been present throughout human history. Understanding their history may help in recognising such conditions today.”

“Identifying both individuals as female and closely related turns this burial into a familial genetic case. The older woman’s milder short stature likely reflects a heterozygous mutation, showing how the same gene affected members of a prehistoric family differently.”

In this case, the disorder expressed itself differently in the two bodies, though they shared the same genetic dysfunction.  But, a note on the importance of care and compassion, as Romito 2 survived thanks to sustained care within her community.

🔗 Sumber: interestingengineering.com

📌 TOPINDIATOURS Update ai: Which Agent Causes Task Failures and When?Researchers f

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: chain.zhang@jiqizhixin.com

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