Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

29,741 stories · RSS feed

arXiv AI

Jun 11

Nonslop: A Gamified Experiment in Human-AI Collaborative Writing

arXiv:2606. 12350v1 Announce Type: new Abstract: The rapid proliferation of large language models (LLMs) raises critical questions about human creativity and individual expression in an era of AI-assisted creation.

By Maria Edwards, Julian Togelius

llms

arXiv AI

Jun 11

Mind the Perspective: Let's Reason Recursively for Theory of Mind

arXiv:2606. 11724v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs.

By Chao Lei, Guang Hu, Meng Yang, Yanbei Jiang, Nir Lipovetzky

llms agents benchmarks

arXiv AI

Jun 11

Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical Assessment

arXiv:2606. 11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes.

By Derek Yohn, Luke Flancher, Mirajul Islam, Khaled Slhoub

llms agents reinforcement-learning

arXiv AI

Jun 11

Harness In-Context Operator Learning with Chain of Operators

arXiv:2606. 12318v1 Announce Type: cross Abstract: Neural operators approximate mappings between function spaces, but often generalize poorly to other operators and usually require fine-tuning or retraining.

By Minghui Yang, Ling Guo, Liu Yang

llms fine-tuning

arXiv AI

Jun 11

Estimating Tail Risks in Language Model Output Distributions

arXiv:2604. 22167v2 Announce Type: replace-cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale.

By Rico Angell, Raghav Singhal, Zachary Horvitz, Zhou Yu, Rajesh Ranganath, Kathleen McKeown, He He

llms benchmarks safety

arXiv AI

Jun 11

Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning

arXiv:2606. 11675v1 Announce Type: new Abstract: Diagnosing pulmonary diseases requires integrating heterogeneous evidence amid phenotypic variability and cross-disease overlap.

By Haoyang Zeng, Yuanxi Fu, Rongzhen Li, Yuming Yang, Xiao Sun, Jingwang Huang, Gujie Shao, Guohui Xiang, Quan Lu, Dongfan Ye, Xuetao Chen, Jiang Zhong, Kaiwen Wei, Zhi Xu

llms nlp reinforcement-learning benchmarks

arXiv AI

Jun 11

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching

arXiv:2606. 11473v1 Announce Type: cross Abstract: Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass.

By Jamie Heredge, Mattia J. Villani, Pranav Deshpande, Akshay Seshadri, Niraj Kumar

llms benchmarks

arXiv AI

Jun 11

APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection

arXiv:2606. 11459v1 Announce Type: cross Abstract: Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential.

By Fei Wang, Si Si, Cho-Jui Hsieh, Inderjit S. Dhillon

llms benchmarks

arXiv AI

Jun 11

Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation

arXiv:2606. 12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.

By Selen Erkan, Bastian Boll, Kristian Kersting, Bj\"orn Deiseroth, Letitia Parcalabescu

llms benchmarks

arXiv AI

Jun 11

Forecasting Future Behavior as a Learning Task

arXiv:2606. 11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs.

By Mosh Levy, Yoav Goldberg, Asa Cooper Stickland

llms fine-tuning

arXiv AI

Jun 11

On the Limits of LLM-as-Judge for Scientific Novelty Assessment

arXiv:2606. 12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas.

By Soumitra Sinhahajari, Navonil Majumder, Soujanya Poria

llms benchmarks

arXiv AI

Jun 11

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

arXiv:2606. 11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction.

By Jiajie Jin, Yuyang Hu, Kai Qiu, Qi Dai, Chong Luo, Guanting Dong, Xiaoxi Li, Tong Zhao, Xiaolong Ma, Gongrui Zhang, Zhirong Wu, Bei Liu, Zhengyuan Yang, Linjie Li, Lijuan Wang, Hongjin Qian, Yutao Zhu, Zhicheng Dou

llms agents

arXiv AI

Jun 11

Preregistration for Experiments with AI Agents

arXiv:2606. 11217v1 Announce Type: cross Abstract: The proliferation of large language models (LLMs) and autonomous AI agents has given rise to a rapidly growing methodological paradigm: "in silico" behavioral experiments.

By Michelle Vaccaro

llms agents

arXiv Machine Learning

Jun 11

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models

arXiv:2606. 11206v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) is the predominant paradigm for aligning large language models (LLMs), yet it suffers from optimization instability and limited generalization.

By Yucheng Zhou, Junwei Sheng, Qianning Wang, Jianbing Shen

llms reinforcement-learning fine-tuning

arXiv AI

Jun 11

MSUE: Multi-Modal Soccer Understanding Expert

arXiv:2606. 12106v1 Announce Type: cross Abstract: This paper presents our solution to the 2026 SoccerNet VQA Challenge.

By Litao Li, Yibo Yu, Yufeng Hu, Zhuo Yang, Jiali Wen, Yixin Chen, Yixi Zhou

llms rag nlp fine-tuning multimodal benchmarks

arXiv AI

Jun 11

VIA-SD: Verification via Intra-Model Routing for Speculative Decoding

arXiv:2606. 12243v1 Announce Type: cross Abstract: Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validate in parallel.

By Yuchen Xian, Yang He, Yunqiu Xu, Yi Yang

llms

arXiv Machine Learning

Jun 11

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

arXiv:2606. 12232v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation.

By Stipe Frkovic, Metod Jazbec, Dan Zhang, Christian A. Naesseth, Ilija Bogunovic, Eric Nalisnick

llms diffusion

arXiv AI

Jun 11

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

arXiv:2606. 11854v1 Announce Type: cross Abstract: There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs).

By Michal Chudoba, Sergey Alyaev, Petra Galuscakova, Tomasz Wiktorski

llms fine-tuning efficiency multimodal benchmarks

arXiv AI

Jun 11

A Physics-Inspired Optimizer: Velocity Regularized Adam

arXiv:2505. 13196v3 Announce Type: replace-cross Abstract: We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its stabilizing effects on various system dynamics.

By Pranav Vaidhyanathan, Lucas Schorling, Natalia Ares, Maike Osborne

llms computer-vision benchmarks

arXiv AI

Jun 11

From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning

arXiv:2606. 11745v1 Announce Type: cross Abstract: Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual inputs and reasoning over intervention effects.

By Haoping Yu, Yuanxi Li, Jing Ma

llms multimodal

Get the daily briefing