Related papers: DockSmith: Scaling Reliable Coding Environments vi…
With the success of deep learning techniques in a broad range of application domains, many deep learning software frameworks have been developed and are being updated frequently to adapt to new hardware features and software libraries,…
Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured…
Container technologies such as Docker have become a crucial component of many software industry practices especially those pertaining to reproducibility and portability. The containerization philosophy has influenced the scientific…
Agentic repository-level code understanding is essential for automating complex software engineering tasks, yet the field lacks reliable benchmarks. Existing evaluations often overlook the long tail topics and rely on popular repositories…
Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current…
AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this…
We propose DeepSim, a reinforcement learning environment build toolkit for ROS and Gazebo. It allows machine learning or reinforcement learning researchers to access the robotics domain and create complex and challenging custom tasks in ROS…
Agentic systems augment large language models with external tools and iterative decision making, enabling complex tasks such as deep research, function calling, and coding. However, their long and intricate execution traces make failure…
Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable and generalizable…
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. The agent uses a bottleneck mechanism over a set-based representation to force the number of…
Containerization allows developers to define the execution environment in which their software needs to be installed. Docker is the leading platform in this field, and developers that use it are required to write a Dockerfile for their…
As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…
The AEC-Bench is a multimodal benchmark for evaluating agentic systems on real-world tasks in the Architecture, Engineering, and Construction (AEC) domain. The benchmark covers tasks requiring drawing understanding, cross-sheet reasoning,…
Recent advances in coding agents have made them capable of planning, editing, running, and testing complex code bases. Despite their growing ability in coding tasks, these systems still struggle to infer and track user intent, especially…
Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn,…
Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-quality data for training and evaluation. To tackle this data scarcity issue, we present AutoSDT,…
Cloud applications are more and more microservice-oriented, but a concrete charting of the microservices architecture landscape -- namely, the space of technical options available for microservice software architects in their…
Multimodal Large Language Models (MLLMs) have revolutionized GUI automation, yet their efficacy is largely established on idealized, single-layer interfaces. This paper identifies a critical reliability gap: state-of-the-art agents face…
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI. Accomplishing this goal requires learning to ground language in perception and embodied actions,…
A composable infrastructure is defined as resources, such as compute, storage, accelerators and networking, that are shared in a pool and that can be grouped in various configurations to meet application requirements. This freedom to 'mix…