Related papers: SR-Platform: An Agentic Pipeline for Natural Langu…
We propose a novel approach to multi-robot collaboration that harnesses the power of pre-trained large language models (LLMs) for both high-level communication and low-level path planning. Robots are equipped with LLMs to discuss and…
Space-air-ground integrated networks (SAGIN) promise ubiquitous 6G connectivity but face significant resource management challenges due to heterogeneous infrastructure, dynamic topologies, and stringent quality-of-service (QoS)…
Significant progress has been made in the area of model-based reinforcement learning. State-of-the-art algorithms are now able to match the asymptotic performance of model-free methods while being significantly more data efficient. However,…
Large Language Models (LLMs) have revolutionized the simulation of agent societies, enabling autonomous planning, memory formation, and social interactions. However, existing frameworks often overlook systematic evaluations for event…
The rapid progress of Large Language Models has advanced agentic systems in decision-making, coordination, and task execution. Yet, existing agentic system generation frameworks lack full autonomy, missing from-scratch agent generation,…
Language models are revolutionizing the biochemistry domain, assisting scientists in drug design and chemical synthesis with high efficiency. Yet current approaches struggle between small language models prone to hallucination and limited…
Generating realistic and controllable traffic scenes from natural language can greatly enhance the development and evaluation of autonomous driving systems. However, this task poses unique challenges: (1) grounding free-form text into…
Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learning-based methods typically model distributions on simple…
We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle…
Learning from few demonstrations to develop policies robust to variations in robot initial positions and object poses is a problem of significant practical interest in robotics. Compared to imitation learning, which often struggles to…
Early-stage specifications of safety-critical systems are typically expressed in natural language, making it difficult to derive formal properties suitable for verification and needed to guarantee safety. While recent Large Language Model…
While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…
Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into…
Automated metasurface design is increasingly important, and recent advances in language-model systems are opening a route toward agentic optical design. Yet modern metasurface applications, from metalenses and holography to optical…
This paper presents a Large Language Model (LLM) based conversational agent system designed to enhance human-machine collaboration in Machine Learning Operations (MLOps). We introduce the Swarm Agent, an extensible architecture that…
Rare, yet critical, scenarios pose a significant challenge in testing and evaluating autonomous driving planners. Relying solely on real-world driving scenes requires collecting massive datasets to capture these scenarios. While automatic…
Recent advances in foundation models have shown promising results in developing generalist robotics that can perform diverse tasks in open-ended scenarios given multimodal inputs. However, current work has been mainly focused on indoor,…
We introduce MLE-Dojo, a Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows. Unlike existing…
We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on…
The ability of robots to interpret human instructions and execute manipulation tasks necessitates the availability of task-relevant tabletop scenes for training. However, traditional methods for creating these scenes rely on time-consuming…