Agentic views for SQL, geo-spatial exploration benchmarks, and motion control advances
ScienceToStartup Editorial
This week's AI research brings sophisticated agent-based solutions to complex data querying and dynamic environments. AV-SQL introduces a novel framework for decomposing intricate Text-to-SQL queries using specialized LLM agents and 'agentic views.' Concurrently, EVGeoQA establishes a new benchmark for evaluating LLMs in dynamic, multi-objective geo-spatial exploration, particularly for electric vehicle scenarios. Finally, MoRight offers a unified approach to motion-controlled video generation, disentangling camera and object motion for greater control and causality.
Use This Via API or MCP
Pillar articles explain the operator narrative around the same proof surfaces your agents can access directly. Use them for context, then drop into REST, MCP, Signal Canvas, or the benchmark and dataset routes for machine-readable execution.

The Rundown
Researchers have introduced AV-SQL, a framework designed to tackle the persistent challenges in Text-to-SQL translation, particularly for complex queries involving large database schemas. Existing methods often falter when schemas exceed LLM context windows or when queries demand multi-step reasoning across numerous tables. AV-SQL addresses this by decomposing complex queries into a pipeline of specialized LLM agents. The core innovation lies in 'agentic views'—Common Table Expressions (CTEs) generated by agents that encapsulate intermediate logic and filter relevant schema elements. This approach allows AV-SQL to process large schemas more effectively. The framework operates in three stages: a rewriter agent clarifies the input query, a view generator agent creates agentic views from schema chunks, and a final agent collaboratively composes these views into the executable SQL query. This modular design aims to improve accuracy and handle intricate data relationships that have previously stumped LLMs.
The details
Why it matters
For startups, AV-SQL offers a path to unlock deeper insights from structured data without requiring extensive SQL expertise. This can democratize data analysis, enabling business intelligence teams to query complex databases more efficiently and accurately, leading to faster decision-making.
The Rundown
Evaluating LLMs in dynamic, real-world geo-spatial environments presents a significant hurdle. Existing benchmarks often focus on static data retrieval, failing to capture the complexities of planning and exploration driven by real-time user location and multiple objectives. To bridge this gap, EVGeoQA has been introduced. This novel benchmark is built around Electric Vehicle (EV) charging scenarios, featuring queries explicitly tied to a user's current coordinates and integrating dual objectives: charging necessity and co-located activity preference. To systematically assess LLM capabilities in these settings, the GeoRover evaluation framework was developed. GeoRover employs a tool-augmented agent architecture to test LLMs' capacity for dynamic, multi-objective exploration. Initial experiments reveal that while LLMs can effectively use tools for sub-tasks, they struggle with long-range spatial exploration. An interesting emergent capability observed is the LLMs' ability to summarize historical exploration trajectories to improve future efficiency.
The details
Why it matters
Startups operating in logistics, navigation, or location-based services can leverage EVGeoQA to rigorously test and improve their LLM-powered agents. Better geo-spatial reasoning is critical for optimizing delivery routes, personalizing user experiences, and enabling autonomous systems to navigate complex, real-world environments effectively.
🎬 Computer Vision
The Rundown
Generating videos with precise motion control—where user-specified actions drive physically plausible scene dynamics and allow for viewpoint adjustments—has been a significant challenge. Existing methods often entangle camera and object motion, treating movement as simple pixel displacement without modeling causal relationships. MoRight introduces a unified framework to address these limitations through disentangled motion modeling. It separates object motion from camera viewpoint control. Object motion is specified in a canonical view and transferred to a target camera via temporal cross-view attention, enabling independent control. Furthermore, MoRight decomposes motion into active (user-driven) and passive (consequential) components, learning motion causality from data. This allows for both forward reasoning—predicting consequences from specified actions—and inverse reasoning—recovering plausible actions from desired outcomes, all while freely adjusting the camera. Experiments on multiple benchmarks demonstrate MoRight's current best performance in generation quality, controllability, and interaction awareness.
The details
Why it matters
For startups in media production, gaming, or virtual reality, MoRight offers a powerful tool for creating dynamic and interactive video content. The ability to precisely control motion and causality opens doors for more realistic simulations, personalized video experiences, and efficient content generation pipelines, reducing production costs and time.
An intuitive platform for deep learning research and production.
A framework for building applications powered by LLMs.
An open platform for managing the full ML lifecycle.
A platform for tracking experiments, datasets, and model performance.
A flexible framework for building and training ML models.
Built to make you extraordinarily productive, Cursor is the best way to code with AI.
Anthropic's Claude sees paid subscriptions double this year, indicating strong user adoption.
Mark Lanier, a lawyer and pastor, successfully represented clients against Meta and Google in a significant case.
ShinyHunters claims a 350GB data theft from the European Commission, though internal systems were reportedly unaffected.
DHS cleared seven staffers accused of misleading a former acting director regarding a polygraph test.
Ross Nordeen, a co-founder at xAI, has reportedly left the company.
A decade-long feud between Sam Altman and Dario Amodei is highlighted, with Amodei reportedly comparing Altman's legal fight to Hitler's conflict with Stalin.
Chess grandmasters are developing new strategies that incorporate less optimal moves to counter AI's influence on perfect play.
A new computer chip material inspired by the human brain could significantly reduce AI energy consumption.
May 29
3D portrait planning, FHIR data generation, and embodied AI unification.
May 28
IPO-Mine dataset, real-time EEG analysis, and physics-grounded robot manipulation.
May 22
Massive text-to-image dataset, LLM agent diagnostics, and AI publishing platforms.