Related papers: ORCA: ORchestrating Causal Agent
Modern database systems allow users to query or process unstructured text or document columns using LLM-powered functions. Users can express an operation in natural language (e.g., "identify if this review mentions billing issues"), with…
Human visual reasoning is characterized by an ability to identify abstract patterns from only a small number of examples, and to systematically generalize those patterns to novel inputs. This capacity depends in large part on our ability to…
The rapid progress in Generative AI and Agent technologies is profoundly transforming enterprise data management and analytics. Traditional database applications and system deployment are fundamentally impacted by AI-driven tools, such as…
Conversational recommender systems (CRS) have advanced with large language models, showing strong results in domains like movies. These domains typically involve fixed content and passive consumption, where user preferences can be matched…
The Semantic Table Annotation (STA) task, which includes Column Type Annotation (CTA) and Cell Entity Annotation (CEA), maps table contents to ontology entities and plays important roles in various semantic applications. However, complex…
LLM agents are increasingly deployed to plan, retrieve, and write with tools, yet evaluation still leans on static benchmarks and small human studies. We present the Agent-Testing Agent (ATA), a meta-agent that combines static code…
Despite the impressive capabilities of Large Language Models (LLMs), existing Conversational Health Agents (CHAs) remain static and brittle, incapable of adaptive multi-turn reasoning, symptom clarification, or transparent decision-making.…
Root Cause Analysis (RCA) is a quality management method that aims to systematically investigate and identify the cause-and-effect relationships of problems and their underlying causes. Traditional methods are based on the analysis of…
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…
Large Language Models (LLMs) have improved programming efficiency, but their performance degrades significantly as requirements scale; when faced with multi-modal documents containing hundreds of scenarios, LLMs often produce incorrect…
This paper presents Compliance Brain Assistant (CBA), a conversational, agentic AI assistant designed to boost the efficiency of daily compliance tasks for personnel in enterprise environments. To strike a good balance between response…
Web-based activities span multiple webpages. However, conventional browsers with stacks of tabs cannot support operating and synthesizing large volumes of information across pages. While recent AI systems enable fully automated web browsing…
Cooperative Multi-Agent Reinforcement Learning (MARL) solves complex tasks that require coordination from multiple agents, but is often limited to either local (independent learning) or global (centralized learning) perspectives. In this…
Causal analysis plays a foundational role in scientific discovery and reliable decision-making, yet it remains largely inaccessible to domain experts due to its conceptual and algorithmic complexity. This disconnect between causal…
Therapeutic discovery remains a formidable challenge, impeded by the fragmentation of specialized domains and the execution gap between computational design and physiological validation. Although generative AI offers promise, current models…
Observational studies can yield clinically actionable evidence at scale, but executing them on real-world databases is open-ended and requires coherent decisions across cohort construction, analysis, and reporting. Prior evaluations of LLM…
Medical diagnosis assistant (MDA) aims to build an interactive diagnostic agent to sequentially inquire about symptoms for discriminating diseases. However, since the dialogue records used to build a patient simulator are collected…
Confounding is a significant obstacle to unbiased estimation of causal effects from observational data. For settings with high-dimensional covariates -- such as text data, genomics, or the behavioral social sciences -- researchers have…
For decades, SQL has been the default language for composing queries, but it is increasingly used as an artifact to be read and verified rather than authored. With Large Language Models (LLMs), queries are increasingly machine-generated,…
LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…