Related papers: Tool-Call Dependency Structure is Linearly Decodab…

Large Language Models (LLMs) increasingly act as function-call agents that invoke external tools to tackle tasks beyond their static knowledge. However, they typically invoke tools one at a time without a global view of task structure. As…

LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime values enter a natural-language prompt, undergo opaque processing inside the LLM, and re-emerge as…

Large language models (LLMs) can now access a wide range of external tools, thanks to the Model Context Protocol (MCP). This greatly expands their abilities as various agents. However, LLMs rely entirely on the text descriptions of tools to…

LLM agents execute in an interleaved reasoning-and-action loop, where future tool calls cannot be launched until the current reasoning step completes. This serial dependency inflates end-to-end latency and leaves the model idle while…

Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool names, descriptions, and return messages. We show that this convenience creates a…

Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model…

Despite remarkable advances in the field, LLMs remain unreliable in distinguishing causation from correlation. Recent results from the Corr2Cause dataset benchmark reveal that state-of-the-art LLMs -- such as GPT-4 (F1 score: 29.08) -- only…

Transformer-based agentic AI is rapidly being deployed on major platforms to help users shop, watch, and navigate content with less effort. While these systems can deliver impressive performance, a key concern is whether they may be less…

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…

When a tool-calling agent picks the wrong tool, the failure is invisible until execution: the email gets sent, the meeting gets missed. As agents take on consequential actions, one bad tool call can do real damage. We currently have no way…

Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces…

Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an…

Large-scale telecom and datacenter infrastructures rely on multi-layered service and resource models, where failures propagate across physical and logical components and affect multiple customers. Traditional approaches to root cause…

Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, and multi-step reasoning. Current tool-using agents usually expose the executed tool…

We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business insights, our target use case, requires decomposing it into executable steps over structured tools…

Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus on the final answers yet overlook the detailed tool usage…

Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as temporal graph neural networks, achieve…

Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across…

Graph learning aims to convert data into graph representations, which are fundamental to many problems in machine learning for CAD, where circuits, layouts, designs, and optimization states are often modeled as graph-structured objects.…

As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical…