Related papers: Concurrency without Model Changes: Future-based As…

Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries through function calling. However, the deployment of these LLMs on the edge has…

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…

We present a framework that takes a concurrent program composed of unsynchronized processes, along with a temporal specification of their global concurrent behaviour, and automatically generates a concurrent program with synchronization…

Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal Gap} between action initiation and completion. Existing…

We have reached a practical and realistic phase in human-support dialogue agents by developing a large language model (LLM). However, when requiring expert knowledge or anticipating the utterance content using the massive size of the…

Function calling (FC) has emerged as a powerful technique for facilitating large language models (LLMs) to interact with external systems and perform structured tasks. However, the mechanisms through which it influences model behavior…

Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this paper, we show that embodied tasks exhibit strong plan locality, where the next plan is…

Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a fundamental constraint in real world teamwork, collaboration…

Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However, tool use is not always beneficial; some calls may be redundant or even harmful. Effective tool use, therefore, hinges on a core LLM decision:…

Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce…

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 Model (LLM) agents significantly extend the capabilities of standalone LLMs, empowering them to interact with external tools (e.g., APIs, functions) and complete various tasks in a self-directed fashion. The challenge of tool…

Recent advancements in Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. While these models excel in general complex reasoning tasks, they still face challenges in…

Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training…

Existing benchmarks for tool-augmented language models (TaLMs) lack fine-grained control over task difficulty and remain vulnerable to data contamination. We present FuncBenchGen, a unified, contamination-free framework that evaluates TaLMs…

LLM agents increasingly act on external systems, yet tool effects are immediate. Under failures, speculation, or contention, losing branches can leak unintended side effects with no safe rollback. We introduce Atomix, a runtime that…

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach struggles with limited data in the context of low-resource…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

Large Language Models (LLMs) have become increasingly capable of interacting with external tools, granting access to specialized knowledge beyond their training data - critical in dynamic, knowledge-intensive domains such as Chemistry and…

While Large Language Models (LLMs) are increasingly used for synthesizing textual PLC programming languages like Structured Text (ST) code, other IEC 61131-3 standard graphical languages like Sequential Function Charts (SFCs) remain…