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

📌 MAROKO133 Eksklusif ai: Which Agent Causes Task Failures and When?Researchers fr

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

📌 MAROKO133 Hot ai: Chinese scientists achieve first manned polar deep dive, robot

China has carried out its first manned deep dive beneath the Arctic ice, as part of its 15th and largest Arctic Ocean scientific expedition, which concluded last month.

The mission also marked the world’s first coordinated operation between a crewed and uncrewed submersible in the polar region. During the dives, researchers collected hundreds of deep-sea samples and gathered data on biodiversity, ocean hydrology, sea ice conditions, and water chemistry. 

The expedition covered a wide area of the central Arctic Ocean, providing valuable insights into deep-sea ecosystems and climate change, with the goal to support data analysis and improve our understanding of the Arctic’s changing environment.

Upgraded Jiaolong submersible leads China’s first crewed dives 

China’s latest Arctic Ocean expedition brought together an advanced research fleet that included the domestically built icebreaker Xue Long 2, the Jidi icebreaker, the research vessel Tansuo 3, and the research ship Shenhai 1 carrying the Jiaolong manned submersible, the South China Morning Post reported.

Departing from Qingdao in eastern Shandong province in July, the fleet sailed as far north as latitude 77.5 degrees, carrying out marine environmental surveys and deep-sea dives, according to CCTV. 

The large-scale mission – the country’s most extensive Arctic expedition to date – concluded on September 26, when the final 100 researchers returned to Shanghai aboard Xue Long 2. The upgraded Jiaolong submersible performed China’s first crewed dives in ice-covered Arctic waters, gathering valuable data and samples from extreme depths.

According to Fu Wentao, chief pilot of the Jiaolong manned submersible, the team expanded the vessel’s usual single-point operating method during the Arctic mission. They carried out a coordinated dive with a remotely operated vehicle, addressing challenges such as underwater communication, positioning accuracy, and synchronized movement. Fu noted that the successful trial marked an important step toward more complex joint operations in future deep-sea expeditions.

Jiaolong submersible collects 183 samples 

In August, China’s Arctic expedition carried out a series of joint dives featuring the Jiaolong manned submersible and a remotely operated vehicle, marking a new milestone in polar research. During these missions, the two vehicles filmed each other underwater while collecting valuable biological and geological material from the Arctic seabed. 

Over the course of more than ten dives, Jiaolong gathered 183 biological samples – including shrimps, sea spiders, and sea anemones – along with sediment, rock, and seawater specimens for further analysis.

According to the National Deep Sea Centre in Qingdao, the biological and geological samples collected during the Arctic dives were of notably higher quality than those obtained through traditional trawling methods. These improved samples are expected to support more precise morphological identification and further scientific study. 

In addition, researchers from the Second Institute of Oceanography under China’s Ministry of Natural Resources employed AI tools and environmental DNA detection techniques to enhance the identification and classification of deep-sea organisms, marking a step forward in the integration of advanced technologies in marine research.

🔗 Sumber: interestingengineering.com