Related papers: Nalar: An agent serving framework

With the advancement of Multimodal Large Language Models (MLLM), LLM-driven visual agents are increasingly impacting software interfaces, particularly those with graphical user interfaces. This work introduces a novel LLM-based multimodal…

Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small…

Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only…

As LLM applications grow more complex, developers are increasingly adopting multi-agent architectures to decompose workflows into specialized, collaborative components, introducing structure that constrains agent behavior and exposes useful…

While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also…

Large Language Models (LLMs) hold great potential for web-based interactive applications, including browser games, online education, and digital storytelling platforms. However, LLM-based conversational agents suffer from spatiotemporal…

Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding and auditable…

In this work, we argue that not all sequence-to-sequence tasks require the strong inductive biases of autoregressive (AR) models. Tasks like multilingual transliteration, code refactoring, grammatical correction or text normalization often…

Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…

Existing LLM agent systems typically select actions from a fixed and predefined set at every step. While this approach is effective in closed, narrowly scoped environments, it presents two major challenges for real-world, open-ended…

Large Language Models (LLMs) have resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput has emerged as a key metric that…

We present an agentic framework, Thinker, which achieves state of art performance in challenging reasoning tasks for realistic customer service scenarios that involve complex business logic and human interactions via long horizons. On the…

Agentic LLM applications increasingly execute user requests as multi-step workflows involving planning, tool use, branching, refinement, and synthesis. In such settings, users experience the end-to-end latency of an entire workflow, not the…

As LLM agent systems take on more complex tasks, they increasingly rely on meta-agents: higher-order agents that operate on other agents, much as managers supervise employees. Whatever a meta-agent does: coordinating agents, halting risky…

Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and reduce hallucinations. However, developing prompting techniques that enable LLM agents to…

AI agents using Large Language Models (LLMs) as foundations have shown promise in solving complex real-world tasks. In this paper, we propose an LLM-based agentic workflow for automating Standard Operating Procedures (SOP). For customer…

Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for agentic multi-step decision making remain underexplored. We…

Agentic reinforcement learning (RL) has emerged as a transformative workload in cloud clusters, enabling large language models (LLMs) to solve complex problems through interactions with real world. However, unlike traditional RL, agentic RL…

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…