📌 TOPINDIATOURS Eksklusif ai: Mamdani Forces Delivery Apps to Pay Back $4.6 Millio

New York City’s mayor isn’t even a month into his term, and he’s already delivering a crushing blow to delivery app companies.

In a bombshell intervention, Zohran Mamdani and Department of Consumer and Worker Protection commissioner Sam Levine announced that three delivery apps will be forced to repay $4.6 million in wages held back from deliveristas, New York City’s app-based delivery workers.

According to NYC Streetblog, the three main culprits being forced to settle are Uber Eats, Fantuan, and Hungry Panda. The three settlements were the result of a sweeping investigation into broader delivery app practices, which included GrubHub and DoorDash.

“The era of giant corporations juicing profits by underpaying workers is over,” Levine said in a statement. “I’m proud that this agency is not only returning full back pay, but is recovering damages and penalties to send a strong message that cheating workers will not be tolerated.”

Per the mayoral administration, Uber Eats unfairly deactivated and underpaid thousands of workers between December 4, 2023, and September 2, 2024. It’s now being forced to pay $3,150,000 in worker relief penalties across over 48,000 workers, in amounts ranging from $8.79 to $276.15.

In addition, Uber Eats will have to pay the city of New York $350,000 in civil fines — a drop in the bucket compared to the $13.7 billion in revenue the company brought in throughout 2024, but a win for the worker-friendly administration all the same.

The decision strikes a major blow to an industry that has historically relied on its political and financial largess to avoid consequences for horrifying worker abuses resulting from algorithmic management systems.

“For years, app companies treated the law as optional — hiding behind algorithms, stealing wages, and deactivating workers without consequence,” Ligia Guallpa, executive director of the Workers’ Justice Project, told NYC Streetblog in a statement. “The scale of these abuses proves what deliveristas have been saying for years: exploitation is not an accident — it’s baked into the app delivery business model.”

James Parrott, a senior fellow at the Center for New York City Affairs at The New School, concurred.

“For far too long, delivery and other online labor platform companies have not only underpaid workers, but deactivated them with abandon, denying workers the ability to make a living,” he said.

Perhaps surprisingly, Uber hasn’t denied any wrongdoing and went as far as to thank officials for bringing light to the issue.

In a statement to NYC Streetblog, Uber spokesman Josh Gold said that “we’re glad to have this resolved.”

“After DCWP notified us of the issue in August 2024, we immediately corrected it, agreed to pay more than the amount owed, and appreciate the new administration moving quickly to bring this to a fair conclusion,” he said.

More on delivery: Delivery Robot Gets Stuck on Train Tracks, Gets Obliterated by Locomotive

The post Mamdani Forces Delivery Apps to Pay Back $4.6 Million Cheated From Drivers appeared first on Futurism.

🔗 Sumber: futurism.com

📌 TOPINDIATOURS Eksklusif ai: Which Agent Causes Task Failures and When?Researcher

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