The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

research1156 agents716 infra561 labs317 culture268 capital253 regulation233 claude175 openai149 safety103 security89 evaluation77 reasoning61 alignment52 benchmarks50 interpretability48

arXiv cs.CLPaper16d ago

Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift

A needed benchmark that surfaces a real gap: most text-to-SQL work measures final query correctness, not whether the model tracks the conversation or recognizes when users change their minds. The patterns tested are genuine: users ask imprecise questions that need clarification, then they retract. If you're building database interfaces with LLMs this shows where models break. The evaluation of 12 models is useful for positioning.

research text-to-sql benchmark llm-evaluation

arXiv cs.CLPaper17d ago

Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL

Text-to-SQL pipelines have become kitchen-sink affairs, and this paper finally measures what actually helps. The finding is deflating: most of the fancy modules are theater, and only execution-feedback refinement pays for itself consistently. If you're building a SQL agent, this tells you what to build and what to skip.

agents sql text-to-sql evaluation

arXiv cs.CLPaper1mo ago

Causal Episodic Memory for Feedback-Driven Agent Repair

Modest but real gains, roughly 3 to 5 points of accuracy on Spider and BIRD, from a lightweight memory layer that avoids fine-tuning. Practical for teams running iterative agent repair loops who want a cheap accuracy bump without touching model weights.

agents research text-to-sql memory