arXiv AI August 3, 2026 By Jungang Zou, Alex Ziyu Jiang, Qixuan Chen

AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers

arXiv:2605. 18476v2 Announce Type: replace-cross Abstract: Coding and computation remain major bottlenecks in Markov chain Monte Carlo (MCMC) workflows, especially as modern sampling algorithms have become increasingly complex and existing probabilistic programming systems remain limited in model support, extensibility, and composability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 18

Structured Inference with Large Language Gibbs

arXiv:2606. 19264v1 Announce Type: new Abstract: The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex world, but accessing this knowledge in a probabilistically coherent manner poses a difficult inference problem.

By Sanghyeok Choi, Henry Gouk, Esmeralda S. Whitammer

llms

arXiv Machine Learning

4d ago

Harnessing Large Language Models to Compile Task-Relevant Context into Bayesian Optimisation

arXiv:2609.36788v1 Announce Type: new Abstract: Incorporating rich task-relevant context, such as domain knowledge and external observations, is a key capability yet remains challenging for Bayesian...

By Zhongwei Yu, Sourabh Roy, Bin Cao, Xue Yan, Anjie Liu, Jun Wang

llms rag benchmarks

arXiv Machine Learning

Aug 4

Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch

arXiv:2608. 00316v1 Announce Type: new Abstract: Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by generic statistical priors.

By Paul Brunzema, Louis Tiao, Nhat Le, Kevin De Angeli, Yao Xuan, Djordje Gligorijevic

llms agents benchmarks

arXiv AI

Sep 4

Grammar-Aligned Decoding

The paper introduces Grammar‑Aligned Decoding (GAD), addressing the issue that conventional grammar‑constrained decoding (GCD) can distort a large language model’s probability distribution, yielding grammatical but low‑likelihood outputs. GAD proposes an adaptive sampling method, Approximate Expected Futures (ASAp), which uses prior samples to over‑approximate future grammaticality, ensuring outputs remain both grammatical and faithful to the model’s conditional probabilities. Experiments on code generation and structured NLP tasks demonstrate that ASAp often produces higher‑likelihood outputs than existing GCD techniques while still enforcing the required grammatical constraints.

By Kanghee Park, Jiayu Wang, Taylor Berg-Kirkpatrick, Nadia Polikarpova, Loris D'Antoni

llms nlp

arXiv AI

Jul 28

Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach

arXiv:2607. 24259v1 Announce Type: new Abstract: Recent work has explored the use of Large Language Models (LLMs) to automate simulation model building, typically by generating executable code directly from natural language descriptions.

By Thomas Monks, Alison Harper, Amy Heather, Navonil Mustafee

llms multimodal benchmarks

arXiv AI

Jul 22

FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis

arXiv:2607. 18260v1 Announce Type: new Abstract: We introduce FindStatBench, an execution benchmark for evaluating large language models on combinatorial code synthesis.

By Soham Dan

llms rag agents benchmarks

One email a morning, machine-written

Related stories

Structured Inference with Large Language Gibbs

Harnessing Large Language Models to Compile Task-Relevant Context into Bayesian Optimisation

Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch

Grammar-Aligned Decoding

Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach

FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis