arXiv:2607. 22642v1 Announce Type: new Abstract: Enterprise coding agents translate natural-language analytical requests into executable code over proprietary APIs, schemas, and metric definitions.
arXiv:2602. 16720v2 Announce Type: replace-cross Abstract: Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments.
arXiv:2605. 12376v2 Announce Type: replace Abstract: Table processing-including cleaning, transformation, augmentation, and matching-is a foundational yet error-prone stage in real-world data pipelines.
arXiv:2606. 02109v1 Announce Type: new Abstract: Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approaches fundamentally different from academic benchmarks.
arXiv:2605. 21027v2 Announce Type: replace-cross Abstract: Enterprise analytics aims to make organizational data accessible for decision-making, yet non-technical users still face barriers when using traditional business intelligence tools or Text-to-SQL systems.
The paper introduces Tool Primitives, a design that replaces rigid API schemas with natural language interfaces for tool calling, enabling seamless inter-tool communication. It builds ToolFace, a repository of over 25,000 functions that LLMs can dynamically retrieve, and HEART, a harness engineering framework that orchestrates tool use with planning, routing, and verification. Experiments show HEART outperforms fine‑tuned models and leading commercial LLMs while cutting API costs by up to 85%.
The paper introduces the DevRev NL2SQL benchmark, comprising 900 execution‑verified queries that feature nested‑type and link‑graph structures, along with the Semantic Depth Score (SDS) to assess analytical reasoning depth. It also presents a cost‑aware single‑generation agentic architecture that includes schema selection, metadata retrieval, and error‑repair components tailored to nested enterprise schemas. On the DevRev benchmark, the system achieves 91.7% answer correctness, outperforming the next‑best baseline by 54.6 percentage points, and remains competitive on the Spider 2.0 Snowflake dataset.
arXiv:2608. 15145v1 Announce Type: new Abstract: Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inference pipelines.
arXiv:2608. 09532v1 Announce Type: cross Abstract: Enterprises increasingly seek to query data lakes using natural language via AI-driven tools like semantic operators or deep research agents.
Text2Dashboard is a prototype that converts natural‑language analytic requests into inspectable dashboards for DataBrain. It uses a Codex plugin and an Agent Runtime that enforce schema constraints, read‑only SQL, and deterministic hooks for approval, audit, and failure handling. The system was evaluated on real DataBrain tasks, achieving high success rates on metadata, SQL, and dashboard composition while handling fault scenarios without unintended side effects.
The paper presents a DataBrain‑specific prototype that converts natural‑language analytic requests into inspectable dashboards. It combines a Codex plugin and an Agent Runtime that use schema‑constrained model decisions, typed tools, persistent state, and deterministic Hooks for approval, audit, checkpointing, recovery, and failure handling. The pipeline resolves entities, discovers metadata, enforces read‑only SQL, composes dashboards, and applies static checks, dynamic preflight, and browser inspection, with the model proposing actions while deterministic software controls execution and records state transitions.
The paper introduces the DevRev NL2SQL benchmark, featuring 900 execution‑verified queries that test natural‑language‑to‑SQL systems on nested, graph‑like enterprise schemas, and proposes the Semantic Depth Score (SDS) as a rubric for analytical reasoning depth. It also presents a cost‑aware, single‑generation agentic architecture that includes schema selection, metadata retrieval, and error‑repair components tailored to these complex schemas. On the DevRev benchmark, the system achieves 91.7% answer correctness, outperforming the next‑best baseline by 54.6 percentage points, and remains competitive on the Spider 2.0 Snowflake dataset.