Related papers: MultiVer: Zero-Shot Multi-Agent Vulnerability Dete…
The recent growth in multi-fidelity uncertainty quantification has given rise to a large set of variance reduction techniques that leverage information from model ensembles to provide variance reduction for estimates of the statistics of a…
Smart contracts have transformed decentralized finance, but flaws in their logic still create major security threats. Most existing vulnerability detection techniques focus on well-supported languages like Solidity, while low-resource…
Multi-agent systems are increasingly equipped with heterogeneous multimodal sensors, enabling richer perception but introducing modality-specific and agent-dependent uncertainty. Existing multi-agent collaboration frameworks typically…
Can generative agents be trusted in multimodal environments? Despite advances in large language and vision-language models that enable agents to act autonomously and pursue goals in rich settings, their ability to reason about safety,…
Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…
Exploratory GUI testing is essential for software quality but suffers from high manual costs. While Multi-modal Large Language Model (MLLM) agents excel in navigation, they fail to autonomously discover defects due to two core challenges:…
EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…
Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large…
Modern Artificial Intelligence (AI) increasingly relies on multi-agent architectures that blend visual and language understanding. Yet, a pressing challenge remains: How can we trust these agents especially in zero-shot settings with no…
Prompt injection constitutes a significant challenge for generative AI systems by inducing unintended outputs. We introduce a multi-agent NLP framework specifically designed to address prompt injection vulnerabilities through layered…
Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes error recognition particularly challenging. Minor errors can…
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…
Real-world visualization tasks involve complex, multi-modal requirements that extend beyond simple text-to-chart generation, requiring reference images, code examples, and iterative refinement. Current systems exhibit fundamental…
Multimodal AI systems are evaluated by downstream task accuracy, but high accuracy does not mean the underlying data is coherent. A model can score well on Visual Question Answering (VQA) while its inputs contradict each other. We introduce…
Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…
Detecting vulnerabilities in source code remains a critical yet challenging task, especially when benign and vulnerable functions share significant similarities. In this work, we introduce VulTrial, a courtroom-inspired multi-agent…
Multimodal Large Language Models (MLLMs) like GPT-4V are capable of reasoning across text and image modalities, showing promise in a variety of complex vision-language tasks. In this preliminary study, we investigate the out-of-the-box…
Zero-shot named entity recognition (NER) aims to develop entity recognition systems from unannotated text corpora. This task presents substantial challenges due to minimal human intervention. Recent work has adapted large language models…
Heavy supervised fine-tuning on a target domain can strongly suppress capabilities that were present in the base model. We study this phenomenon in formal mathematics using Goedel-Prover-V2, an open-source model heavily trained on 1.8…
Maximizing performance on available GPU hardware is an ongoing challenge for modern AI inference systems. Traditional approaches include writing custom GPU kernels and using specialized model compilers to tune high-level code for specific…