Large language models

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

25,303 stories · RSS feed

arXiv AI

Jun 30

Data and Evaluation Closed-Loop for Model Capability Enhancement

arXiv:2606. 28471v1 Announce Type: new Abstract: Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it only retrospectively, compressing samples, prompts, decoding, and scoring rules into one noisy score.

By Zhixuan Li, Jiangan Yuan, Han Xu

llms benchmarks

arXiv AI

Jun 30

Recursive Self-Evolving Agents via Held-Out Selection

arXiv:2606. 28374v1 Announce Type: new Abstract: LLM agents are increasingly improved without weight updates by evolving a natural-language artifact, such as reflections, workflows, playbooks, cheatsheets, or optimized prompts, that conditions a frozen policy.

By Michael Nguyen, Quoc Nguyen, Paul Vuong

llms agents benchmarks

arXiv Machine Learning

Jun 30

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

arXiv:2602. 12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety.

By Yannick Assogba, Jacopo Cortellazzi, Javier Abad, Pau Rodriguez, Xavier Suau, Arno Blaas

llms diffusion safety

arXiv AI

Jun 30

Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds

arXiv:2606. 29654v1 Announce Type: new Abstract: Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and when it should be escalated to human review.

By Mengdie Flora Wang, Haochen Xie, Guanghui Wang, Devin Zhang, Jae Oh Woo

llms agents benchmarks safety

arXiv AI

Jun 30

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

arXiv:2606. 29537v1 Announce Type: new Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to reveal the limitations of frontier agents.

By Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong, Weiming Wu, Jiayang Sun, Jiamin Song, Kaiqian Cui, Bowen Wang, Haoyuan Wu, Yitong Li, Dunjie Lu, Haikong Lu, Qi Zhen, Xinyuan Wang, Jiaqi Deng, Yuhao Yang, Cheng Chen, Boyuan Zheng, Alex Su, Xiao Yu, Hao Zou, Saaket Agashe, Xing Han Lu, Manpreet Kaur, Zhengyang Qi, Vincent Sunn Chen, Frederic Sala, Dayiheng Liu, Junyang Lin, Zhou Yu, Yu Su, Siva Reddy, Xin Eric Wang, Peng Qi, Tianbao Xie, Tao Yu

llms agents benchmarks safety

arXiv Machine Learning

Jun 30

Contrastive vision-language learning with paraphrasing and negation

arXiv:2511. 16527v2 Announce Type: replace-cross Abstract: Contrastive vision-language models continue to be the dominant approach for image-text retrieval.

By Kwun Ho Ngan, Saman Sadeghi Afgeh, Joe Townsend, Artur d'Avila Garcez

llms rag diffusion computer-vision multimodal

arXiv AI

Jun 30

It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents

arXiv:2606. 27944v1 Announce Type: cross Abstract: Phone-use Agents can execute complex tasks end to end across real mobile applications.

By Yiming Sun, Chen Chen, Zifan Zhou, Mi Zhang

llms agents robotics safety

arXiv AI

Jun 30

MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentatio

arXiv:2606. 28419v1 Announce Type: cross Abstract: Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification.

By Teerath Kumar, Raja Vavekanand, Muhammad Turab

llms diffusion computer-vision benchmarks

arXiv AI

Jun 30

Latent Bridges for Multi-Table Question Answering

arXiv:2606. 28916v1 Announce Type: cross Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering.

By Simone Varriale, Tamara Cucumides, Floris Geerts, Paolo Papotti

llms nlp

arXiv AI

Jun 30

Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict

arXiv:2601. 03546v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate decision-making tasks involving personal data sharing, where privacy concerns and prosocial motivations can push choices in opposite directions.

By Guanyu Chen, Chenxiao Yu, Xiyang Hu

llms safety

arXiv AI

Jun 30

Fine-Tuning General-Purpose Large Language Models for Agricultural Applications:A Reproducible Framework and Evaluation Protocol Based on Qwen3-8B

arXiv:2606. 28992v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) have demonstrated strong abilities in opendomain question answering, information extraction, and text generation.

By Zhaoyang Li, Ruijie Zhang, Jiaqi Liu, Zhaoji Sun

llms nlp fine-tuning safety

arXiv Machine Learning

Jun 30

Attractor States Emerge in Multi-Turn LLM Conversations

arXiv:2606. 30571v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in open-ended multi-agent settings, but the long-run dynamics of model--model interaction remain poorly understood.

By Ting-Wen Ko, Jonas Geiping

llms agents diffusion reinforcement-learning

arXiv Machine Learning

Jun 30

xGR: Efficient Generative Recommendation Serving at Scale

arXiv:2512. 11529v3 Announce Type: replace Abstract: Recommendation system delivers substantial economic benefits by providing personalized predictions.

By Qingxiao Sun, Tongxuan Liu, Shen Zhang, Siyu Wu, Peijun Yang, Haotian Liang, Menxin Li, Xiaolong Ma, Zhiwei Liang, Ziyi Ren, Minchao Zhang, Yifan Wang, Xinyu Liu, Ke Zhang, Hailong Yang, Depei Qian

llms efficiency benchmarks

arXiv AI

Jun 30

Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense

arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.

By Subhadip Mitra

llms benchmarks safety

arXiv AI

Jun 30

Diagnosing and Mitigating Context Rot in Long-horizon Search

arXiv:2606. 29718v1 Announce Type: cross Abstract: Extensive context has become the norm as Large Language Models (LLMs) are increasingly deployed in long-horizon tasks.

By Shijie Xia, Yikun Wang, Zhen Huang, Pengfei Liu

llms efficiency benchmarks

arXiv AI

Jun 30

Mechanistically Eliciting Latent Behaviors in Language Models

arXiv:2606. 29604v1 Announce Type: cross Abstract: We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes.

By Andrew Mack, Nina Panickssery, Alexander Matt Turner

llms safety

arXiv AI

Jun 30

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers

arXiv:2606. 29844v1 Announce Type: cross Abstract: The quadratic computational cost of traditional attention mechanisms poses a major bottleneck to the scalability and practical deployment of large language models (LLMs), particularly in long-context scenarios.

By Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin Xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui

llms

arXiv AI

Jun 30

Assessing the Business Process Modeling Competences of Large Language Models

arXiv:2601. 21787v2 Announce Type: replace-cross Abstract: The creation of Business Process Model and Notation (BPMN) models is a complex and time-consuming task requiring both domain knowledge and proficiency in modeling conventions.

By Chantale Lauer, Peter Pfeiffer, Alexander Rombach, Nijat Mehdiyev

llms fine-tuning benchmarks

arXiv AI

Jun 30

Little Brains, Big Feats: Exploring Compact Language Models

arXiv:2606. 30062v1 Announce Type: cross Abstract: While large language models have been dominating the research landscape recently, small language models remain highly relevant across various domains; yet, they receive far less attention.

By Dari Baturova, Elena Bruches, Ivan Chernov, Roman Derunets, Arsenii Fomin, Andrey Kostin

llms rag benchmarks

arXiv AI

Jun 30

On the Faithfulness of Post-Hoc Concept Bottleneck Models

arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.

By Laines Schmalwasser, Jan Blunk, Niklas Penzel, Julia Niebling, Joachim Denzler

llms multimodal benchmarks

Get the daily briefing