Enterprise Document Intelligence [Vol.1 #2D] - What data scientists say when asked, what the model actually does under the hood, and why the honest answer changes your architecture decisions in enterprise RAG
The post How Does a RAG Reranker Really Work? appeared first on Towards Data Science.
Even the best AI models can suck at chess The launch of ChatGPT had an interesting effect on the online chess discourse. Chess has already long been conquered by machines. As early as 1996 a computer (IBM’s Deep Blue) was able to beat the human world champion, grandmaster Garry Kasparov, in a game w...
When my oldest child was born, I immediately set up Gmail and Twitter accounts in her name. I broadly announced her birth online and proceeded to plaster her photo across all sorts of platforms. In short, I began creating her digital footprint long before she could stand on her own two feet. Fast-f...
AI models flub these intelligence tests. Can you fare any better?
Puzzles and games have been central to AI development since the very beginning. Just as we humans like to test our smarts with crosswords or logic puzzles, developers can test how far models have advanced with a gaming gauntlet. The term “machine learning” was popularized in a 1959 article by the IB...
Why most agents are just flowcharts in disguise, and what to build instead.
The post Is Agentic AI Just Automation? appeared first on Towards Data Science.
IBM Releases Granite 4.2: Bringing Native Reasoning and Agentic RL to Open Enterprise Models
IBM has released Granite 4.2, a family of open reasoning language models in 3B, 8B, and 30B sizes, all under Apache 2.0. Every model exposes a thinking / low-effort / non-thinking switch and native tool calling. The 8B and 30B additionally go through an agentic RL block that trains them to edit code...
RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation
arXiv:2608.23568v1 Announce Type: new
Abstract: Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a memory entry, summary, typed record, or raw excerpt. We introduce RENDER, a benchmark control that fix...
ESQ-Bench: A Multi-Tier Enterprise Oracle Benchmark for Evaluating NL2SQL Dialect Generalization and Silent Semantic Divergence
arXiv:2608.23569v1 Announce Type: new
Abstract: State-of-the-art Natural Language to SQL (NL2SQL) models report execution accuracy exceeding 89 percent on established benchmarks such as Spider and BIRD. However, these benchmarks rely on simplified academic schemas and open-source SQL dialects that ...
LLM Agents Perform Controlled Experiments Using Simulation Models
arXiv:2608.23622v1 Announce Type: new
Abstract: Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding how a system responds to inter...
A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts
arXiv:2608.23626v1 Announce Type: new
Abstract: Foundation models for astronomy are trained on survey pixels together with the catalogue products derived from those pixels. Those catalogues are incomplete at a measurable rate, and a model trained on both inherits that incompleteness as a systematic...
TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery
arXiv:2608.23631v1 Announce Type: new
Abstract: Multi-objective materials discovery with LLM agents is often limited not only by how many candidates can be proposed, but by how effectively each costly property evaluation informs the next search step. Existing agents mainly store evaluated candidate...
Equivariant Cellular Sheaves for Molecular Electronic Structure: Bridging Sheaf Cohomology and E(3)-Equivariant Hamiltonian Learning
arXiv:2608.23571v1 Announce Type: new
Abstract: Equivariant message-passing networks are the standard model for molecular property and interatomic-potential prediction, and recent work predicts the electronic Hamiltonian itself in an E(3)-equivariant way. Separately, topological deep learning has e...
Data Predictability Shapes Weibull Weight-Scale Growth in Transformer Training
arXiv:2608.23573v1 Announce Type: new
Abstract: A trained transformer's weight magnitudes can be summarized by a two-parameter Weibull distribution whose shape $k \approx 1.2$ is stable across layers and models, so the scale $\lambda$ carries most training-induced movement. What corpus property set...
From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers
arXiv:2608.23660v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used to provide prior causal knowledge for structural causal discovery, yet whether their direct-edge judgments and confidence can be trusted remains unclear. We systematically evaluate 12 instruction-tune...
Renormalization Group Flow Matching for Scalable Local Generative Modeling
arXiv:2608.23696v1 Announce Type: new
Abstract: Despite their remarkable success in modeling complex data, generative models face a fundamental tradeoff. Global approaches can capture full structural coherence but suffer from high computational costs, while local models are efficient but often fail...
Response Renormalization for Critical Deep Equilibrium Models
arXiv:2608.23725v1 Announce Type: new
Abstract: Deep Equilibrium Models (DEQs) compute predictions from a hidden representation unchanged by the model update. Training through this equilibrium uses implicit differentiation and requires solving an adjoint system built from the residual Jacobian. If ...
How loveholidays is making everyone a builder with Codex
Discover how loveholidays uses OpenAI Codex to make software development accessible across the business, helping teams turn ideas into products faster.