Related papers: Guideline-Grounded Evidence Accumulation for High-…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Static analysis plays a crucial role in software vulnerability detection, yet faces a persistent precision-scalability tradeoff. In large codebases like the Linux kernel, traditional static analysis tools often generate excessive false…

Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from third parties or self-generated, these skills are often…

Medical imaging has revolutionized diagnosis, yet unnecessary procedures are rising, exposing patients to radiation and stress, limiting equitable access, and straining healthcare systems. The American College of Radiology Appropriateness…

Retrieval augmented generation (RAG) systems provide a method for factually grounding the responses of a Large Language Model (LLM) by providing retrieved evidence, or context, as support. Guided by this context, RAG systems can reduce…

Multimodal clinical reasoning in the field of gastrointestinal (GI) oncology necessitates the integrated interpretation of endoscopic imagery, radiological data, and biochemical markers. Despite the evident potential exhibited by Multimodal…

The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained signals are often overshadowed by dominant, high-fidelity image content (e.g., the main…

As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on model activations have shown promise for detecting…

Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies. However, most current approaches use minor variants of a Graph Convolutional Network (GCN), which applies…

We propose using validated behavioral hypotheses as a lens for evaluating human-likeness in LLM-based agents. Our key idea is simple: If an agent is human-like, a population of such agents should reach the same inferential conclusion as the…

Grounding the reasoning ability of large language models (LLMs) for embodied tasks is challenging due to the complexity of the physical world. Especially, LLM planning for multi-agent collaboration requires communication of agents or credit…

Event argument extraction identifies arguments for predefined event roles in text. Existing work evaluates this task with exact match (EM), where predicted arguments must align exactly with annotated spans. While suitable for span-based…

We present a novel deep generative semi-supervised framework for credit card fraud detection, formulated as time series classification task. As financial transaction data streams grow in scale and complexity, traditional methods often…

Multi-agent systems have extended the capability of agentic AI. Instead of single inference passes, multiple agents perform collective reasoning to derive high quality answers. However, existing multi-agent orchestration relies on static…

Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This work introduces a multi-agent refinement framework designed…

Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulnerability: spurious correlations, where retrieved memory carries miscorrelated evidence and…

The prefill stage in long-context LLM inference remains a computational bottleneck. Recent token-ranking heuristics accelerate inference by selectively processing a subset of semantically relevant tokens. However, existing methods suffer…

Medical Large Vision-Language Models (Med-LVLMs) have shown strong potential in multimodal diagnostic tasks. However, existing single-agent models struggle to generalize across diverse medical specialties, limiting their performance. Recent…

Multiple myeloma is managed through sequential lines of therapy over years to decades, with each decision depending on cumulative disease history distributed across dozens to hundreds of heterogeneous clinical documents. Whether LLM-based…

Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LLM-generated contents…