-- In collaborative robotic applications, human and robot have to work together during a whole shift for executing a sequence of jobs. The performance of the human robot team can be enhanced by scheduling the right tasks to the human and the robot. The scheduling should consider the task execution constraints, the variability in the task execution by the human, and the job quality of the human. Therefore, it is necessary to dynamically schedule the assigned tasks. In this paper, we propose a two-layered architecture for task allocation and scheduling in a collaborative cell. Job quality is explicitly considered during the allocation of the tasks and over a sequence of jobs. The tasks are dynamically scheduled based on the real time monitoring of the human's activities. The effectiveness of the proposed architecture is experimentally validated. In recent years, industrial setting has been supported by a constant increase in the use of collaborative robotics (see e.g. The shift towards collaborative robotics can significantly change the quality of the job for the human. In fact, collaborative robots can take over dull, heavy or dangerous tasks making the life of the human easier.

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi-step information needs. Our position is that Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research. These systems transcend conventional information search techniques by tightly integrating autonomous reasoning, iterative retrieval, and information synthesis into a dynamic feedback loop. We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn. We also introduce a test-time scaling law to formalize the impact of computational depth on reasoning and search. Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking. All the related resources, including industry products, research papers, benchmark datasets, and open-source implementations, are collected for the community in https://github.com/DavidZWZ/Awesome-Deep-Research.

With the rise of generative AI, industry interest in software agents is growing. Given the stochastic nature of generative AI-based agents, their effective and safe deployment in organizations requires robust governance, which can be facilitated by agentic business process management. However, given the nascence of this new-generation agent notion, it is not clear what BPM practitioners consider to be an agent, and what benefits, risks and governance challenges they associate with agent deployments. To investigate how organizations can effectively govern AI agents, we conducted a qualitative study involving semi-structured interviews with 22 BPM practitioners from diverse industries. They anticipate that agents will enhance efficiency, improve data quality, ensure better compliance, and boost scalability through automation, while also cautioning against risks such as bias, over-reliance, cybersecurity threats, job displacement, and ambiguous decision-making. To address these challenges, the study presents six key recommendations for the responsible adoption of AI agents: define clear business goals, set legal and ethical guardrails, establish human-agent collaboration, customize agent behavior, manage risks, and ensure safe integration with fallback options. Additionally, the paper outlines actions to align traditional BPM with agentic AI, including balancing human and agent roles, redefining human involvement, adapting process structures, and introducing performance metrics. These insights provide a practical foundation for integrating AI agents into business processes while preserving oversight, flexibility, and trust.

In autonomous driving, recent research has increasingly focused on collaborative perception based on deep learning to overcome the limitations of individual perception systems. Although these methods achieve high accuracy, they rely on high communication bandwidth and require unrestricted access to each agent's object detection model architecture and parameters. These constraints pose challenges real-world autonomous driving scenarios, where communication limitations and the need to safeguard proprietary models hinder practical implementation. To address this issue, we introduce a novel late collaborative framework for 3D multi-source and multi-object fusion, which operates solely on shared 3D bounding box attributes-category, size, position, and orientation-without necessitating direct access to detection models. Our framework establishes a new state-of-the-art in late fusion, achieving up to five times lower position error compared to existing methods. Additionally, it reduces scale error by a factor of 7.5 and orientation error by half, all while maintaining perfect 100% precision and recall when fusing detections from heterogeneous perception systems. These results highlight the effectiveness of our approach in addressing real-world collaborative perception challenges, setting a new benchmark for efficient and scalable multi-agent fusion.

Trajectory prediction is an essential step in the pipeline of an autonomous vehicle. Inaccurate or inconsistent predictions regarding the movement of agents in its surroundings lead to poorly planned maneuvers and potentially dangerous situations for the end-user. Current state-of-the-art deep-learning-based trajectory prediction models can achieve excellent accuracy on public datasets. However, when used in more complex, interactive scenarios, they often fail to capture important interdependencies between agents, leading to inconsistent predictions among agents in the traffic scene. Inspired by the efficacy of incorporating human preference into large language models, this work fine-tunes trajectory prediction models in multi-agent settings using preference optimization. By taking as input automatically calculated preference rankings among predicted futures in the fine-tuning process, our experiments--using state-of-the-art models on three separate datasets--show that we are able to significantly improve scene consistency while minimally sacrificing trajectory prediction accuracy and without adding any excess computational requirements at inference time.

Autonomous scientific research, capable of independently conducting complex experiments and serving non-specialists, represents a long-held aspiration. Achieving it requires a fundamental paradigm shift driven by artificial intelligence (AI). While autonomous experimental systems are emerging, they remain confined to areas featuring singular objectives and well-defined, simple experimental workflows, such as chemical synthesis and catalysis. We present an AI-native autonomous laboratory, targeting highly complex scientific experiments for applications like autonomous biomolecular engineering. This system autonomously manages instrumentation, formulates experiment-specific procedures and optimization heuristics, and concurrently serves multiple user requests. Founded on a co-design philosophy of models, experiments, and instruments, the platform supports the co-evolution of AI models and the automation system. This establishes an end-to-end, multi-user autonomous laboratory that handles complex, multi-objective experiments across diverse instrumentation. Our autonomous laboratory supports fundamental nucleic acid functions-including synthesis, transcription, amplification, and sequencing. It also enables applications in fields such as disease diagnostics, drug development, and information storage. Without human intervention, it autonomously optimizes experimental performance to match state-of-the-art results achieved by human scientists. In multi-user scenarios, the platform significantly improves instrument utilization and experimental efficiency. This platform paves the way for advanced biomaterials research to overcome dependencies on experts and resource barriers, establishing a blueprint for science-as-a-service at scale.

Modern biomedical research is defined by both immense opportunity and staggering complexity. As a cornerstone of science, it generates vast quantities of data from large-scale experiments, but this progress is hampered by a research landscape that is profoundly fragmented (1-3). The knowledge, specialized software, and databases required to make discoveries are numerous, constantly evolving, and dispersed, forcing researchers to expend significant time and effort on the manual and labor-intensive task of discovering, learning, and integrating these disparate resources. While the advent of AI agents holds the promise of automating this intricate work (4-6), current systems inherit a critical limitation: they typically rely on manually curated, static toolsets (7-14). This approach is inefficient, fails to scale, and cannot keep pace with the rapid evolution of biomedical science, leaving the agents perpetually behind the cutting edge. This raises a critical question: Can we design a self-evolving agent that transcends these limitations by automatically discovering and integrating new tools, continuously updating its knowledge base, and iteratively upgrading its own capabilities through direct experience? Here we present STELLA, a generalist biomedical AI agent designed around the core principle of self-evolution (15). STELLA learns and improves from every problem it solves, continuously enhancing its own reasoning strategies and technical abilities.

At Google's I/O 2025 event in May, the company showed off a digital assistant that didn't just answer questions; it helped work on a bicycle repair by finding a matching user manual, locating a YouTube tutorial, and even calling a local store to ask about a part, all with minimal human nudging. Such capabilities could soon extend far outside the Google ecosystem. The vision is exciting: Intelligent software agents that act like digital coworkers, booking your flights, rescheduling meetings, filing expenses, and talking to each other behind the scenes to get things done. But if we're not careful, we're going to derail the whole idea before it has a chance to deliver real benefits. And when expectations get out of hand, a backlash isn't far behind.

The Thirty-Seventh Annual Conference on Innovative Applications of Artificial Intelligence (IAAI 2025), which took place alongside AAAI 2025, serves as a showcase for successful applications and novel uses of AI. One such application is the Onboard Artificial Intelligence Research (OnAIR) platform, introduced by Evana Gizzi and colleagues in their paper OnAIR: Applications of The NASA On-Board Artificial Intelligence Research Platform. This open-source software pipeline and cognitive architecture tool has been designed to aid space research and missions. We spoke to Evana, Artificial Intelligence Research Lead at NASA Goddard Space Flight Center, about the OnAIR platform, some of the particular challenges of deploying AI-based solutions in space, and how the tool has been used so far. OnAIR is an open-source software pipeline and cognitive architecture tool.

Let's start with the term "agent" itself. Right now, it's being slapped on everything from simple scripts to sophisticated AI workflows. There's no shared definition, which leaves plenty of room for companies to market basic automation as something much more advanced. That kind of "agentwashing" doesn't just confuse customers; it invites disappointment. We don't necessarily need a rigid standard, but we do need clearer expectations about what these systems are supposed to do, how autonomously they operate, and how reliably they perform. And reliability is the next big challenge.