Large language models

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

28,285 stories · RSS feed

arXiv AI

Jun 16

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

arXiv:2511. 08577v3 Announce Type: replace-cross Abstract: Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications.

By Tianyu Fu, Yichen You, Zekai Chen, Guohao Dai, Huazhong Yang, Yu Wang

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 16

Enhancing LLM Safety Through a Theoretical Minimax Game Lens

arXiv:2502. 05163v2 Announce Type: replace-cross Abstract: The rapid advancement of large language models (LLMs) necessitates effective mechanisms to ensure their responsible deployment by accurately distinguishing unsafe content from benign content.

By Yihe Deng, Yu Yang, Junkai Zhang, Wei Wang, Bo Li

llms reinforcement-learning efficiency benchmarks safety

arXiv AI

Jun 16

Rational Sparse Autoencoder

arXiv:2606. 14990v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK.

By Naiyu Yin, Yue Yu

llms fine-tuning efficiency safety

arXiv AI

Jun 16

OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models

arXiv:2606. 16774v1 Announce Type: new Abstract: Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw.

By Tianyi Lin, Chuanyu Sun, Jingyi Zhang, Changxu Wei, Huanjin Yao, Shunyu Liu, Xikun Zhang, Liu Liu, Jiaxing Huang

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 16

VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA

arXiv:2606. 16092v1 Announce Type: cross Abstract: Real-world documents combine text with tables, charts, photographs, and diagrams arranged in diverse layouts, yet existing research on multimodal large language models (MLLMs) for document QA predominantly produces text-only responses, underutilizing these visual elements.

By Young Rok Jang, Hyesoo Kong, Kyunghwan An, Jae Sub Huh, Gyeonghun Kim, Stanley Jungkyu Choi

llms fine-tuning multimodal

arXiv AI

Jun 16

P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs

arXiv:2606. 16753v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become embedded in everyday communication, capturing regional linguistic variation is essential for reliable and equitable language use.

By Rafael Ferreira, In\^es Vieira, In\^es Calvo, James Furtado, Iago Paulo, Diogo Tavares, Diogo Gl\'oria-Silva, David Semedo, Jo\~ao Magalh\~aes

llms benchmarks safety

arXiv AI

Jun 16

Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models

arXiv:2606. 16825v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count - dominated by the expert parameters - must be held in training and inference memory.

By Martin Jaggi

llms efficiency benchmarks

arXiv AI

Jun 16

Semantic Flip: Synthetic OOD Generation for Robust Refusal in Embodied Question Answering and Spatial Localization

arXiv:2606. 16898v1 Announce Type: cross Abstract: Detecting unanswerable user queries remains essential for the reliable deployment of real-world embodied agents.

By Dongbin Na, Chanwoo Kim, Giyun Choi, Dooyoung Hong

llms agents nlp robotics multimodal benchmarks

arXiv AI

Jun 16

XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models

arXiv:2606. 16137v1 Announce Type: cross Abstract: Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making.

By Yupei Li, Qiyang Sun, Xiaoliang Wu, Chenxi Wang, Berrak Sisman, Bj\"orn W. Schuller

llms multimodal

arXiv AI

Jun 16

Service-Induced Congestion in Memory-Constrained LLM Serving

arXiv:2606. 15555v1 Announce Type: cross Abstract: In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated token.

By Ruicheng Ao, Jing Dong, Gan Luo, David Simchi-Levi

llms efficiency

arXiv AI

Jun 16

Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems

arXiv:2606. 15242v1 Announce Type: cross Abstract: Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse.

By Yi Xie, Jiawei Du, Yu Cheng, Jiuan Zhou, Zhaoxia Yin

llms agents benchmarks

arXiv AI

Jun 16

Scribby: A Multi-Level LLM Framework for Semantic Video Analysis

arXiv:2606. 14762v1 Announce Type: cross Abstract: As video content continues to expand across educational platforms, recorded lectures, and live-streamed entertainment, the need for efficient and structured analysis of long-form footage has increased \cite{1}.

By Julian Abelarde, Hugo Garrido-Lestache Belinchon

llms rag nlp

arXiv AI

Jun 16

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

arXiv:2603. 15952v2 Announce Type: replace Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex scientific tasks.

By Jacopo Teneggi, S. M. Bargeen A. Turzo, Tanya Marwah, Alberto Bietti, P. Douglas Renfrew, Vikram Khipple Mulligan, Siavash Golkar

llms agents

arXiv AI

Jun 16

AI Engram: In Search of Memory Traces in Artificial Intelligence

arXiv:2606. 14997v1 Announce Type: new Abstract: Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces analogous to biological memory units remains an open question.

By Jea Kwon, Dong-Kyum Kim, Jiwon Kim, Yonghyun Kim, Woong Kook, Meeyoung Cha

llms robotics

arXiv AI

Jun 16

Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation

arXiv:2606. 15077v1 Announce Type: new Abstract: We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries.

By Kyle Gao, Joel Cumming, Jonathan Li, Linlin Xu, David A. Clausi

llms agents robotics safety

arXiv AI

Jun 16

Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative Screening

arXiv:2606. 14788v1 Announce Type: cross Abstract: Voice-based screening offers a scalable and non-invasive way to assess neurodegenerative diseases such as Alzheimer's disease (AD) and Parkinson's disease (PD), but their staging remains challenging due to the difficulty of integrating heterogeneous data.

By Qingfeng Zhang, Yuanxiong Guo, Yanmin Gong

llms rag multimodal

arXiv AI

Jun 16

A Definition of Good Explanations and the Challenges Explaining LLM Outputs

arXiv:2606. 14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs.

By Louis Mahon, Elliot Ford, Callum Hackett

llms

arXiv AI

Jun 16

Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models

arXiv:2606. 16808v1 Announce Type: new Abstract: While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries.

By Ke Miao, Jiaxin Li, Hongliang Chen, Yuke Hu, Zhan Qin

llms reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 16

Formalizing and Mitigating Structural Distortion in LLM Attention for Zero-Shot Graph Reasoning

arXiv:2606. 15633v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs).

By Donald Loveland, Puja Trivedi, Ari Weinstein, Edward W Huang, Danai Koutra

llms rag benchmarks

arXiv AI

Jun 16

Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories

arXiv:2602. 02028v2 Announce Type: replace Abstract: Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a central challenge.

By Ya Gao, Kalle Kujanp\"a\"a, Pekka Marttinen, Harri Valpola, Alexander Ilin

llms efficiency

Get the daily briefing