Related papers: Firefly: Illuminating Large-Scale Verified Tool-Ca…

GitHub's Copilot generates code quickly. We investigate whether it generates good code. Our approach is to identify a set of problems, ask Copilot to generate solutions, and attempt to formally verify these solutions with Dafny. Our formal…

Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers…

While Multimodal Large Language Models have achieved human-like performance on many visual and textual reasoning tasks, their proficiency in fine-grained spatial understanding, such as route tracing on maps remains limited. Unlike humans,…

Training deep learning (DL) models across Graphics Processing Unit (GPU) clusters is technically challenging. One aspect is that users have to compose command lines to adapt to the heterogeneous launchers, schedulers, affinity options, DL…

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks…

Large Language Model (LLM)-based code assistants have emerged as a powerful application of generative AI, demonstrating impressive capabilities in code generation and comprehension. A key requirement for these systems is their ability to…

Large Language Models (LLMs), with their exceptional ability to handle a wide range of tasks, have driven significant advancements in tackling reasoning and planning tasks, wherein decomposing complex problems into executable workflows is a…

Website Fingerprinting (WFP) uses deep learning models to classify encrypted network traffic to infer visited websites. While historically effective, prior methods fail to generalize to modern web environments. Single-page applications…

Data cleaning is a time-consuming and error-prone manual process, even with modern workflow tools such as OpenRefine. We present AutoDCWorkflow, an LLM-based pipeline for automatically generating data-cleaning workflows. The pipeline takes…

Recent advances in LLM Multi-Agent Systems enable scalable orchestration of sub-agents, each coordinating hundreds or thousands of tools or Model Context Protocol (MCP) servers. However, existing retrieval methods typically match queries…

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) leverage external tools primarily through generating the API request to enhance task completion efficiency. The accuracy of API request generation significantly determines the capability of LLMs to accomplish…

The Model Context Protocol (MCP) is emerging as a standard interface through which LLM agents invoke external tools, and a growing ecosystem of MCP servers now mediates access to vendor services. Most of these servers target vendors that…

In the digital age, ensuring the correctness, safety, and reliability of software through formal verification is paramount, particularly as software increasingly underpins critical infrastructure. Formal verification, split into theorem…

Training large language models (LLMs) at scale requires parallel execution across thousands of devices, incurring enormous computational costs. Yet, these costly distributed trainings are rarely verified, leaving them prone to silent errors…

Reward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize process reward models…

Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibits inconsistent interaction representations, largely overlooks…

Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this.…

Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…

High-level synthesis (HLS) transforms an algorithmic description of hardware from a higher abstraction (e.g., C/C++) into a register-transfer level (RTL) design, offering reduced development time and greater flexibility in design space…