IT operationsScaling Enterprise Cloud Agents to Thousands of APIs: An Empirical Study of Agent Architecture and MCP Tool BoundariesAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningFrustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer SupportAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningGLS Chatbot: A Governed Multi-Agent Conversational System for Domain-Specific Customer ServiceAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningWhen Evaluators Cry Wolf: Lessons from Production LLM-as-Judge Evaluation in Educational AIAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningCoEvoLoop: Closed-Loop RL Training of Customer-Service Agents by Co-Evolving Environment, Reward, and PolicyAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningFrom Synthetic to Localized: Benchmarking Multilingual Intent Classification in Logistics Customer ServiceAssociation for Computational LinguisticsResearch paper Oct 2026
IT operationsOpenDC-Infer-LC: Benchmarking Production-Valid Long-Context and RAG LLM ServingAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsSchemaToken: Tokenizing Database Schemas for Efficient and Robust Text-to-SQL LinkingAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsAuditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL PipelineAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsPULSAR: Pooled Unified Late-interaction Search And Retrieval for Enterprise Visual Document RAGAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsFrom Benchmarks to Production: A Text-to-SQL System for Complex Financial DataAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningBeyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System EvaluationAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsA Practitioner’s Guide to Systematic Prompt Evaluation for Information ExtractionAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningMINCE: Shrinking LLM Evaluation Datasets via Few-Model Monte Carlo CalibrationAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsWhen Does User-Scoped Glossary Injection Recover ASR-Corrupted Domain Terms in Meeting Summarization? Separating Term Recovery from…Association for Computational LinguisticsResearch paper Oct 2026
Data & analyticsCemLit-IE: Schema-Constrained LLM Extraction for Traceable Cement Strength DatabasesAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsRe:CAP - Auditing Retrieval Coverage in Production RAG PipelinesAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsSumRank: Aligning Summarization Models for Long-Document Listwise RerankingAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsSession-Guided Pre-training for Query Understanding: Constraining Mask Prediction and Improving Query Fine-tunabilityAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsOntology-Driven Structural Regularization for Document-Level Relation ExtractionAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsLong Document Reconstruction Unlocks Scalable Long-Context RLVRAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsA Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation SummarizationAssociation for Computational LinguisticsResearch paper Oct 2026
Data & analyticsSPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided MergingAssociation for Computational LinguisticsResearch paper Oct 2026
AI & machine learningLLP: LLM-Based Product Pricing in E-commerceAssociation for Computational LinguisticsResearch paper Oct 2026
