Related papers: Agentic DAG-Orchestrated Planner Framework for Mul…

LLMs have advanced text-to-SQL generation, yet monolithic architectures struggle with complex reasoning and schema diversity. We propose AGENTIQL, an agent-inspired multi-expert framework that combines a reasoning agent for question…

Recent advances in Large Language Models (LLMs) have significantly improved complex reasoning capabilities. Retrieval-Augmented Generation (RAG) has further extended these capabilities by grounding generation in dynamically retrieved…

Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large language models (LLMs), when integrated into well-designed frameworks (i.e.,…

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…

This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency…

With the rise of artificial intelligence (AI), applying large language models (LLMs) to mathematical problem-solving has attracted increasing attention. Most existing approaches attempt to improve Operations Research (OR) optimization…

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing…

Existing multimodal document question-answering (QA) systems predominantly rely on flat semantic retrieval, representing documents as a set of disconnected text chunks and largely neglecting their intrinsic hierarchical and relational…

Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs), typically from unstructured texts and structured graphs. While recent progress has advanced text-based RAG to multi-turn reasoning…

Agentic Retrieval-Augmented Generation (RAG) is a new paradigm where the reasoning model decides when to invoke a retriever (as a "tool") when answering a question. This paradigm, exemplified by recent research works such as Search-R1,…

In question answering (QA), different questions can be effectively addressed with different answering strategies. Some require a simple lookup, while others need complex, multi-step reasoning to be answered adequately. This observation…

Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Existing multimodal RAG systems remain limited by two…

The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While Retrieval-Augmented Generation (RAG) offers a solution,…

Existing Retrieval-Augmented Generation (RAG) methods for code struggle to capture the high-level architectural patterns and cross-file dependencies inherent in complex, theory-driven codebases, such as those in algorithmic game theory…

Designing task-oriented dialogue systems is a challenging research topic, since it needs not only to generate utterances fulfilling user requests but also to guarantee the comprehensibility. Many previous works trained end-to-end (E2E)…

Retrieval-Augmented Generation (RAG), by integrating non-parametric knowledge from external knowledge bases into models, has emerged as a promising approach to enhancing response accuracy while mitigating factual errors and hallucinations.…

This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We…

The rapid expansion of web content has made on-device AI assistants indispensable for helping users manage the increasing complexity of online tasks. The emergent reasoning ability in large language models offer a promising path for…

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…

This technical brief introduces Deep Agent, an advanced autonomous AI system designed to manage complex multi-phase tasks through a novel hierarchical task management architecture. The system's foundation is built on our Hierarchical Task…