Related papers: Nalar: An agent serving framework
Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…
Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…
The growing adoption of Large Language Models (LLMs) across various domains has driven the demand for efficient and scalable AI-serving solutions. Deploying LLMs requires optimizations to manage their significant computational and data…
Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from…
Recent advances in large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions. However, applying reinforcement learning (RL) to train LLM agents in multi-turn,…
Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the…
Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit…
While large language model-based multi-agent systems have shown strong potential for complex reasoning, how to effectively organize multiple agents remains an open question. In this paper, we introduce OrgAgent, a company-style hierarchical…
Large Language Model (LLM)-based applications are increasingly deployed across various domains, including customer service, education, and mobility. However, these systems are prone to inaccurate, fictitious, or harmful responses, and their…
Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving…
Ultra-reliable low latency communications (URLLC) service is envisioned to enable use cases with strict reliability and latency requirements in 5G. One approach for enabling URLLC services is to leverage Reinforcement Learning (RL) to…
Next-generation (NextG) cellular networks are expected to manage dynamic traffic while sustaining high performance. Large language models (LLMs) provide strategic reasoning for 6G planning, but their computational cost and latency limit…
The increasing complexity of user demands necessitates automation frameworks that can reliably translate open-ended instructions into robust, multi-step workflows. Current monolithic agent architectures often struggle with the challenges of…
Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challenge. Most existing approaches rely on manually designed…
While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address…
Contemporary multi-agent systems encounter persistent challenges in cross-platform interoperability, dynamic task scheduling, and efficient resource sharing. Agents with heterogeneous implementations often lack standardized interfaces;…
Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation tasks require coordinated multi-agent workflows, where…
AI-RAN consolidates AI services and Radio Access Network (RAN) functions onto a unified, GPU-accelerated infrastructure at the network edge. However, compute sharing between real-time RAN functions and highly heterogeneous AI services…
Agentic workflows commonly coordinate multiple models and tools with complex control logic. They are quickly becoming the dominant paradigm for AI applications. However, serving them remains inefficient with today's frameworks. The key…
Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming…