📌 MAROKO133 Hot ai: Researchers from PSU and Duke introduce “Multi-Agent Systems A
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
📌 MAROKO133 Eksklusif ai: Watch: 1,250-mile-range nuclear missile test-fired from
India successfully test-fired its nuclear-capable Agni-Prime intermediate-range ballistic missile from a rail-based mobile launcher on Wednesday.
The launch, which took place on September 24, 2025, was carried out jointly by India’s state-run Defense Research and Development Organization (DRDO) and the Strategic Forces Command (SFC), according to a statement from the Ministry of Defense.
Agni-Prime, or Agni-P, is part of India’s next-generation missile program designed to strike targets at ranges up to 2,000 kilometers (1,250 miles).
It incorporates advanced guidance, warhead, and communication features, and is engineered to be lighter and more accurate than its predecessors.
The latest trial was distinguished by its use of a specially designed rail-based mobile launcher system, the first such launch in India’s missile development history.
Rail-based missile launchers
Rail-based missile launchers are self-contained train carriages that can transport and fire ballistic missiles from anywhere along a rail network.
This deployment method offers strategic and operational advantages, such as increased mobility, reduced detection risk, and the ability to reposition assets during conflict quickly.
The system tested by India can traverse the country’s extensive rail network without any special infrastructure modifications, allowing for rapid relocation and reduced launch preparation time.
Officials stated the launcher also includes advanced communication suites and robust protection mechanisms, ensuring launch capability under adverse conditions.
The concept of rail-mobile missile launchers is not new on the global stage. The former Soviet Union pioneered intercontinental ballistic missiles (ICBMs) on trains during the Cold War, recognizing the value of dispersed, mobile assets to withstand a first-strike scenario.
China has also developed and fielded its own rail-based missile systems, using them as part of an overall strategy to complicate surveillance and targeting by adversaries.
The United States explored similar projects but abandoned them largely due to cost and changes in strategic doctrine.
Importance in nuclear deterrence
The induction of rail-based mobile missile launchers enhances survivability, a core tenet of credible nuclear deterrence.
Fixed missile silos, while hardened, are potentially vulnerable to enemy first strikes.
Mobile systems, whether road or rail-launched, offer flexibility, allowing for unpredictable movement of launchers, thereby complicating targeting by any adversary and ensuring the ability to retaliate.
In India’s case, integrating rail-based mobile launchers with the Agni-P system fits into the nation’s doctrine of assured retaliation to maintain an effective second-strike capability.
India uses both road and rail launchers to distribute its nuclear weapons across the country. This strategy minimizes their attack risk and creates uncertainty for anyone considering launching a surprise strike.
Senior DRDO scientists and SFC officers witnessed the recent launch, which the Ministry of Defense said had met all mission objectives, with the missile’s trajectory tracked by multiple ground stations throughout its flight.
India has introduced road-mobile versions of the Agni-P after successfully testing them. Adding a rail-based system will strengthen India’s strategic defenses.
Experts see this development as a sign that India is committed to updating its military capabilities in response to changing security challenges in the region.
The successful test is expected to accelerate the induction of rail-based mobile systems into the country’s strategic forces, joining a select group of nations with such capabilities.
Rail-based missile launchers could improve India’s military readiness as tensions increase in Asia, showing the country’s goal is to keep a reliable nuclear deterrent against potential threats.
🔗 Sumber: interestingengineering.com
🤖 Catatan MAROKO133
Artikel ini adalah rangkuman otomatis dari beberapa sumber terpercaya. Kami pilih topik yang sedang tren agar kamu selalu update tanpa ketinggalan.
✅ Update berikutnya dalam 30 menit — tema random menanti!
