Related papers: SmartFlow Reinforcement Learning and Agentic AI fo…

The rapid development of interactive and autonomous AI systems signals our entry into the agentic era. Training and evaluating agents on complex agentic tasks such as software engineering and computer use requires not only efficient model…

Over the past decade, machine learning model complexity has grown at an extraordinary rate, as has the scale of the systems training such large models. However there is an alarmingly low hardware utilization (5-20%) in large scale AI…

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…

In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under…

Deep reinforcement learning (DRL) is emerging as a powerful tool for fluid-dynamics research, encompassing active flow control, autonomous navigation, turbulence modeling and discovery of novel numerical schemes. We introduce SmartFlow, a…

Bike-sharing systems play a crucial role in easing traffic congestion and promoting healthier lifestyles. However, ensuring their reliability and user acceptance requires effective strategies for rebalancing bikes. This study introduces a…

Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensive. Scaling RL to agentic LLMs requires supporting complex…

Bike-sharing systems (BSS) provide a sustainable urban mobility solution, but ensuring their reliability requires effective rebalancing strategies to address stochastic demand and prevent station imbalances. This paper proposes…

Stream applications are widely deployed on the cloud. While modern distributed streaming systems like Flink and Spark Streaming can schedule and execute them efficiently, streaming dataflows are often dynamically changing, which may cause…

Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and…

AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow,…

Analog/mixed-signal circuits are key for interfacing electronics with the physical world. Their design, however, remains a largely handcrafted process, resulting in long and error-prone design cycles. While the recent rise of AI-based…

Traffic signal control is an emerging application scenario for reinforcement learning. Besides being as an important problem that affects people's daily life in commuting, traffic signal control poses its unique challenges for reinforcement…

Large-scale online ride-sharing platforms have substantially transformed our lives by reallocating transportation resources to alleviate traffic congestion and promote transportation efficiency. An efficient fleet management strategy not…

This paper proposes a fully dynamic Deep Reinforcement Learning (DRL) method for rebalancing dockless bike-sharing systems, overcoming the limitations of periodic, system-wide interventions. We model the service through a graph-based…

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…

Dynamic dispatching is one of the core problems for operation optimization in traditional industries such as mining, as it is about how to smartly allocate the right resources to the right place at the right time. Conventionally, the…

Reinforcement learning (RL) has become the pivotal post-training technique for large language model (LLM). Effectively scaling reinforcement learning is now the key to unlocking advanced reasoning capabilities and ensuring safe,…

Traffic flow prediction is an important part of smart transportation. The goal is to predict future traffic conditions based on historical data recorded by sensors and the traffic network. As the city continues to build, parts of the…

This paper presents AgentFlow, a MAS-based framework for programmable distributed systems in heterogeneous cloud-edge environments. It introduces logistics objects and abstract agent interfaces to enable dynamic service flows and modular…