Large language models

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

31,384 stories · RSS feed

arXiv AI

Jun 2

InFerActive: Interactive Tree-Based Exploration of LLM Sampling for Safety Evaluation

arXiv:2512. 10234v2 Announce Type: replace-cross Abstract: Even LLMs that appear safe during evaluation can still produce harmful responses in deployment.

By Junhyeong Hwangbo, Soohyun Lee, Hyeon Jeon, Kyochul Jang, Minsoo Cheong, Youngjae Yu, Jinwook Seo

llms safety

arXiv Machine Learning

Jun 2

Exploiting weight-space symmetries for approximating curvature

arXiv:2606. 00442v1 Announce Type: new Abstract: Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep networks.

By Artem Artemev, Rui Xia, Benjamin M. Boyd, Youjing Yu, Felix Dangel, Guillaume Hennequin, Alberto Bernacchia

llms efficiency benchmarks

arXiv Machine Learning

Jun 2

From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection

arXiv:2602. 03018v2 Announce Type: replace Abstract: Outlier detection (OD) is widely used in practice; but its effective deployment on new tasks is hindered by lack of labeled outliers, which makes algorithm and hyperparameter selection notoriously hard.

By Xueying Ding, Haomin Wen, Simon Kl\"uttermann, Leman Akoglu

llms benchmarks

arXiv AI

Jun 2

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

arXiv:2604. 03893v2 Announce Type: replace Abstract: Current multimodal benchmarks for scientific reasoning primarily evaluate local information extraction -- models recognize symbols and values and then perform textual inference.

By Zeyu Wang, Jingye Xu, Xiaogang Li, Peiyao Xiao, Qinhao Kong, Ben Wang, Chengliang Xu, Zichao Chen, Bing Zhao, Hu Wei

llms multimodal benchmarks

arXiv Machine Learning

Jun 2

Task-Induced Representational Invariances Depend on Learning Objective in Deep RL

arXiv:2606. 01868v1 Announce Type: new Abstract: Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience.

By Manu Srinath Halvagal, Sebastian Lee, SueYeon Chung

llms reinforcement-learning fine-tuning

arXiv AI

Jun 2

NILC: Discovering New Intents with LLM-assisted Clustering

arXiv:2511. 05913v2 Announce Type: replace-cross Abstract: New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems.

By Hongtao Wang, Renchi Yang, Wenqing Lin

llms rag benchmarks

arXiv AI

Jun 2

Continuous Reasoning for Vision-Language-Action

arXiv:2606. 00229v1 Announce Type: cross Abstract: Natural language is a powerful reasoning medium for language and vision-language models, but it is mismatched to the granularity of continuous control.

By Yueh-Hua Wu, Tatsuya Matsushima, Kei Ota

llms robotics multimodal

arXiv Machine Learning

Jun 2

Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention

arXiv:2602. 07223v2 Announce Type: replace Abstract: Long-context large language model (LLM) inference has become the norm for today's AI applications.

By Yikang Yue, Yuqi Xue, Jian Huang

llms efficiency benchmarks

arXiv Machine Learning

Jun 2

From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction

arXiv:2511. 12081v2 Announce Type: replace-cross Abstract: Despite massive investments in scale, deep models for click-through rate (CTR) prediction often exhibit rapidly diminishing returns -- a stark contrast to the {predictable scaling laws} seen in large language models (LLMs).

By Bencheng Yan, Yuejie Lei, Zhiyuan Zeng, Zheye Deng, Di Wang, Kaiyi Lin, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng

llms benchmarks safety

arXiv Machine Learning

Jun 2

Beyond Procedure: Substantive Fairness in Conformal Prediction

arXiv:2602. 16794v2 Announce Type: replace-cross Abstract: Conformal prediction (CP) offers distribution-free uncertainty quantification for machine learning models, yet its interplay with fairness in downstream decision-making remains underexplored.

By Pengqi Liu, Zijun Yu, Mouloud Belbahri, Arthur Charpentier, Masoud Asgharian, Jesse C. Cresswell

llms safety

arXiv AI

Jun 2

MindZero: Learning Online Mental Reasoning With Zero Annotations

arXiv:2606. 00240v1 Announce Type: new Abstract: Effective real-world assistance requires AI agents with robust Theory of Mind (ToM): inferring human mental states from their behavior.

By Shunchi Zhang, Jin Lu, Chuanyang Jin, Yichao Zhou, Zhining Zhang, Tianmin Shu

llms agents reinforcement-learning multimodal

arXiv AI

Jun 2

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills

arXiv:2503. 05641v4 Announce Type: replace-cross Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks.

By Justin Chih-Yao Chen, Sukwon Yun, Elias Stengel-Eskin, Tianlong Chen, Mohit Bansal

llms agents benchmarks

arXiv AI

Jun 2

TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning

arXiv:2508. 12551v2 Announce Type: replace-cross Abstract: Linux kernel tuning is essential for optimizing operating system (OS) performance, yet remains challenging due to the complex kernel space, sparse performance feedback, and strong workload sensitivity.

By Hongyu Lin, Yuchen Li, Haoran Luo, Zhenghong Lin, Libo Zhang, Mingjie Xing, Yanjun Wu

llms agents reinforcement-learning

arXiv AI

Jun 2

Structure Enables Effective Self-Localization of Errors in LLMs

arXiv:2602. 02416v2 Announce Type: replace Abstract: Self-correction in language models remains elusive.

By Ankur Samanta, Akshayaa Magesh, Ayush Jain, Kavosh Asadi, Youliang Yu, Daniel Jiang, Boris Vidolov, Kaveh Hassani, Paul Sajda, Jalaj Bhandari, Yonathan Efroni

llms agents

arXiv AI

Jun 2

Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization

arXiv:2606. 01252v1 Announce Type: cross Abstract: Multi-target cross-lingual text summarization (MTXLS), which summarizes a source document into multiple target languages, is increasingly important as users consume content in diverse languages, but remains underexplored.

By Sangwon Ryu, Yihong Liu, Mingyang Wang, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee, Hinrich Schuetze

llms nlp benchmarks

arXiv AI

Jun 2

Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults

arXiv:2505. 19489v2 Announce Type: replace Abstract: The Linux kernel is a critical system, serving as the foundation for numerous systems.

By Zhenhao Zhou, Zhuochen Huang, Yike He, Chong Wang, Jiajun Wang, Yijian Wu, Xin Peng, Yiling Lou

llms agents benchmarks

arXiv AI

Jun 2

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

arXiv:2606. 00357v1 Announce Type: new Abstract: Training strong large language models (LLMs) requires high-quality supervision, which is often scarce.

By Qi Sun, Siyue Zhang, Yulin Chen, Yuxiang Xue, Ru Peng, Chen Zhao

llms agents fine-tuning benchmarks safety

arXiv Machine Learning

Jun 2

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness

arXiv:2606. 00124v1 Announce Type: cross Abstract: Positional embeddings (PEs) in Vision Transformers (ViTs) are known to impact performance and robustness, but their role in shaping internal spatial representations is not well understood.

By Mahmoud Mannes

llms rag

arXiv AI

Jun 2

Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents

arXiv:2606. 00476v1 Announce Type: new Abstract: Do LLM agents act on the reasoning they state?

By Yufeng Wang

llms agents

arXiv Machine Learning

Jun 2

Contrastive Representation Regularization for Vision-Language-Action Models

arXiv:2510. 01711v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs).

By Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin

llms robotics multimodal benchmarks

Get the daily briefing