Tag
Argo-Bench introduces an evaluation framework of 210 enterprise-scale data science tasks built on a simulated food-delivery platform with an ERP warehouse of 235 tables and 7.5 billion rows, testing agents that must navigate and act rather than just generate SQL. The strongest of 14 frontier and open-weight models averages only 59.5 points, highlighting a significant gap in real-world data agent capabilities.
This paper presents a method for balancing supervised fine-tuning and reinforcement learning to train long-horizon advertising agents, demonstrating that targeted RL reduces data leakage and improves performance in enterprise analytics tasks.
The paper presents a small analytical algebra for governed data analysis, demonstrating that a deterministic policy-executed approach outperforms runtime planning in preserving analytical meaning and evidence across experiments.
This paper introduces a governed analytics framework that pairs language models for intent interpretation with deterministic policy execution of pre-approved programs, achieving full reliability where runtime-planning agents failed.
This paper introduces a production enterprise analytics system that inverts the interaction model from question-first to analyst-first through domain-expert skills and knowledge compilation, enabling proactive analytics with verified metrics and suggested questions.
This paper proposes a multi-agent framework built on CrewAI for automated conversational business intelligence, using five specialized AI agents to process queries, retrieve data, and generate insights, with evaluation showing significant accuracy and quality improvements over baselines.
This paper presents SSAS (Syntactic & Semantic Context Assessment Summarization), a framework designed to improve consistency in LLM-based sentiment prediction by reducing noise and variance through hierarchical classification and iterative summarization. Empirical evaluation on three industry-standard datasets shows up to 30% improvement in data quality and reliability for enterprise decision-making.