Related papers: LVLMs as inspectors: an agentic framework for cate…

Applying reinforcement learning (RL) to real-world tasks requires converting informal descriptions into a formal Markov decision process (MDP), implementing an executable environment, and training a policy agent. Automating this process is…

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Self-Admitted Technical Debt (SATD) refers to technical compromises explicitly admitted by developers in natural language artifacts such as code comments, commit messages, and issue trackers. Among its types, Architecture Technical Debt…

The rise of Agentic applications and automation in the Voice AI industry has led to an increased reliance on Large Language Models (LLMs) to navigate graph-based logic workflows composed of nodes and edges. However, existing methods face…

We present the Comprehensive Verilog Design Problems (CVDP) benchmark, a new dataset and infrastructure to advance LLM and agent research in hardware design and verification. CVDP includes 783 problems across 13 task categories, covering…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes fifteen failure-detection tools and two root-cause analysis…

As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…

With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…

We study the problem of determining whether a piece of text has been authored by a human or by a large language model (LLM). Existing state of the art logits-based detectors make use of statistics derived from the log-probability of the…

Point defects play a central role in driving the properties of materials. First-principles methods are widely used to compute defect energetics and structures, including at scale for high-throughput defect databases. However, these methods…

Fine-tuning object detection (OD) models on combined datasets assumes annotation compatibility, yet datasets often encode conflicting spatial definitions for semantically equivalent categories. We propose an agentic label harmonization…

The demand for efficient large language model (LLM) inference has propelled the development of dedicated accelerators. As accelerators are vulnerable to hardware faults due to aging, variation, etc, existing accelerator designs often…

Large Language Model (LLM)-based Multi-Agent Systems (MAS) enable complex problem-solving but introduce significant debugging challenges, characterized by long interaction traces, inter-agent dependencies, and delayed error manifestation.…

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

Autonomous Driving Systems (ADS) are safety-critical, where failures can be severe. While Metamorphic Testing (MT) is effective for fault detection in ADS, existing methods rely heavily on manual effort and lack automation. We present…

Large Language Models (LLMs) have emerged as promising tools in software development, enabling automated code generation and analysis. However, their knowledge is limited to a fixed cutoff date, making them prone to generating code…

Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, they require…

The use of LLM-based applications as a means to accelerate and/or substitute human labor in the creation of language resources and dataset is a reality. Nonetheless, despite the potential of such tools for linguistic research, comprehensive…

Speech Large Language Models (SLLMs) enable high-level emotion reasoning but often produce ungrounded, text-biased judgments without verifiable acoustic evidence. In contrast, self-supervised speech encoders such as WavLM provide strong…