Related papers: JudgeFlow: Agentic Workflow Optimization via Block…

AI systems can generate outputs at scale, but most outputs require human approval before release. This creates a bottleneck: humans cannot keep pace with AI-generated volume. A natural response is to insert an LLM-judge that screens outputs…

Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and…

Hardware design automation faces challenges in generating high-quality Verilog code efficiently. This paper introduces VFlow, an automated framework that optimizes agentic workflows for Verilog code generation. Unlike traditional approaches…

The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical,…

While small language models (SLMs) have shown promise on various reasoning tasks, their ability to judge the correctness of answers remains unclear compared to large language models (LLMs). Prior work on LLM-as-a-judge frameworks typically…

LLM-as-a-Judge refers to the automatic modeling of preferences for responses generated by Large Language Models (LLMs), which is of significant importance for both LLM evaluation and reward modeling. Although generative LLMs have made…

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but optimizing LLM-based agentic systems remains challenging due to the vast search space of agent configurations, prompting strategies, and…

Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external…

Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation across multiple log sources, a task that is usually…

Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy,…

Despite the remarkable progress of large language models (LLMs), the capabilities of standalone LLMs have begun to plateau when tackling real-world, complex tasks that require interaction with external tools and dynamic environments.…

Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification.…

Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven…

Large Language Models (LLMs) have demonstrated impressive performance across diverse domains, yet they still encounter challenges such as insufficient domain-specific knowledge, biases, and hallucinations. This underscores the need for…

Power grid fault diagnosis is a critical process hindered by its reliance on manual, error-prone methods. Technicians must manually extract reasoning logic from dense regulations and attempt to combine it with tacit expert knowledge, which…

We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to synthesize the correct program that solves the problem and…

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc…

Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

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…