Related papers: AgentSM: Semantic Memory for Agentic Text-to-SQL

Agents equipped with search tools have emerged as effective solutions for knowledge-intensive tasks. While Large Language Models (LLMs) exhibit strong reasoning capabilities, their high computational cost limits practical deployment for…

Agentic AI systems, built upon large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligence, autonomy, collaboration, and decision-making across enterprise and societal domains. This review presents a…

Optimizing large-language model (LLM) training on distributed domain-specific accelerator systems presents significant challenges due to its complex optimization space. Existing optimization methods, however, rely on time-consuming manual…

Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics. We introduce…

Open-sourced Large Language Models (LLMs) have achieved great success in various NLP tasks, however, they are still far inferior to API-based models when acting as agents. How to integrate agent ability into general LLMs becomes a crucial…

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…

The surge in popularity of large language models (LLMs) has opened doors for new approaches to the creation of interactive agents. However, managing and interpreting the temporal behavior of such agents over the course of a potentially…

Small language models (SLMs; 1-12B params, sometimes up to 20B) are sufficient and often superior for agentic workloads where the objective is schema- and API-constrained accuracy rather than open-ended generation. We synthesize recent…

Recent breakthroughs in Large Language Models (LLMs) have led to the emergence of agentic AI systems that extend beyond the capabilities of standalone models. By empowering LLMs to perceive external environments, integrate multimodal…

Agentic frameworks powered by Large Language Models (LLMs) can be useful tools in scientific workflows by enabling human-AI co-creation. A key challenge is recommending the next steps during workflow creation without relying solely on LLMs,…

The rapid shift from stateless large language models (LLMs) to autonomous, goal-driven agents raises a central question: When is agentic AI truly necessary? While agents enable multi-step reasoning, persistent memory, and tool…

Recent Text-to-SQL methods leverage large language models (LLMs) by incorporating feedback from the database management system. While these methods effectively address execution errors in SQL queries, they struggle with database mismatches…

Large language models have demonstrated excellent performance in many tasks, including Text-to-SQL, due to their powerful in-context learning capabilities. They are becoming the mainstream approach for Text-to-SQL. However, these methods…

Recent years have witnessed remarkable progress in automatic speech recognition (ASR), driven by advances in model architectures and large-scale training data. However, two important aspects remain underexplored. First, Word Error Rate…

Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex,…

We present \textbf{Turn}, a compiled, actor-based programming language -- statically typed for schema inference, dynamically typed at the value level -- for agentic software: programs that reason and act autonomously by delegating inference…

Semantic communications (SemCom), as one of the key technologies for 6G, is shifting networks from bit transmission to semantic information exchange. On this basis, introducing agentic artificial intelligence (AI) with perception, memory,…

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency…

Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a…