Related papers: OMG-Agent: Toward Robust Missing Modality Generati…

Retrieval-Augmented Generation (RAG) systems are usually defined by the combination of a generator and a retrieval component that extracts textual context from a knowledge base to answer user queries. However, such basic implementations…

Large language models (LLMs) achieve strong results on knowledge graph question answering (KGQA), but most benchmarks assume complete knowledge graphs (KGs) where direct supporting triples exist. This reduces evaluation to shallow retrieval…

Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal,…

Large language models (LLMs) exhibit strong symbolic and compositional reasoning, yet they struggle with time series question answering as the data is typically transformed into an LLM-compatible modality, e.g., serialized text, plotted…

The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these deficiencies, we propose a principled engineering framework…

Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathematical formulation,…

Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding. However, processing extensive videos such as 24-hour CCTV footage or full-length films…

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required for accurate clinical diagnosis. Existing methods typically rely on static, linear mappings…

Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks through iterative optimization methods.However, these models generally lack effective self-correction mechanisms, making it…

Industrial anomaly generation is a crucial method for alleviating the data scarcity problem in anomaly detection tasks. Most existing anomaly synthesis methods rely on single-step generation mechanisms, lacking complex reasoning and…

With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve-then-generate paradigm toward more sophisticated agentic…

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,…

The Object-Oriented Method for Requirements Authoring and Management (OOMRAM) is a requirements reuse framework that relies on exact identifier matching and rigid templates, limiting its ability to adapt specifications across diverse…

Open-Vocabulary Object Detection (OVOD) aims to enable detectors to generalize across categories by leveraging semantic information. Although existing methods are pretrained on large vision-language datasets, their inference is still…

Generating molecules that satisfy precise numeric constraints over multiple physicochemical properties is critical and challenging. Although large language models (LLMs) are expressive, they struggle with precise multi-objective control and…

Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks but struggles with complex questions. Agentic RAG extends this paradigm by replacing…

Agent memory shapes how Large Language Model (LLM)-powered agents, akin to the human brain, progressively refine themselves through environment interactions. Existing paradigms remain constrained: parametric memory forcibly adjusts model…

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

Text-to-video generation models have shown significant progress in the recent years. However, they still struggle with generating complex dynamic scenes based on compositional text prompts, such as attribute binding for multiple objects,…