Large language models

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

31,046 stories · RSS feed

arXiv AI

Jun 9

Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation

arXiv:2605. 03058v2 Announce Type: replace-cross Abstract: A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms.

By Francesco Sovrano, Gabriele Dominici, Marc Langheinrich

llms efficiency benchmarks safety

arXiv AI

Jun 9

Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces

arXiv:2605. 02950v2 Announce Type: replace-cross Abstract: Transformer-based semantic encoders are effective for retrieval, but in many deployments the recurring bottleneck is online query encoding rather than offline corpus indexing.

By Mohit Kumar, Somayeh Kargaran, Bernhard A. Moser, Manuela Gei{\ss}

llms rag benchmarks

arXiv AI

Jun 9

Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents

arXiv:2606. 07904v1 Announce Type: new Abstract: Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or what task state it produces.

By Rahul Suresh Babu, Laxmipriya Ganesh Iyer

llms agents

arXiv AI

Jun 9

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model

arXiv:2603. 25184v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks.

By Jiahao Wu, Ning Lu, Shengcai Liu, Kun Wang, Yanting Yang, Bailong Lin, Chen Jason Zhang, Li Qing, Ke Tang

llms reinforcement-learning benchmarks

arXiv AI

Jun 9

WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI

arXiv:2605. 16972v2 Announce Type: replace-cross Abstract: Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement.

By Jingjing Li, Zhi Liu, Xiyao Jin, Tatsuki Fushimi, Yoichi Ochiai

llms robotics

arXiv AI

Jun 9

Post-Trained MoE Can Skip Half Experts via Self-Distillation

arXiv:2605. 18643v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner.

By Xingtai Lv, Li Sheng, Kaiyan Zhang, Yichen You, Siyan Gao, Xueheng Luo, Yuxin Zuo, Yuchen Fan, Junlin Yang, Ganqu Cui, Bingning Wang, Fan Yang, Youbang Sun, Ning Ding, Bowen Zhou

llms efficiency benchmarks

arXiv AI

Jun 9

Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers

arXiv:2606. 08292v1 Announce Type: new Abstract: In mechanistic interpretability, attention heads are commonly elevated to role claims (e.

By Philip Quirke

llms benchmarks safety

arXiv AI

Jun 9

Hybrid E-Assessment in Higher Education: Semi-Automated Grading of Paper-Based Written Examinations

arXiv:2606. 08855v1 Announce Type: new Abstract: This paper examines the limitations of fully digital and partially digital e-assessment approaches in summative examinations in higher education.

By Hartwig Grabowski, Michael Canz

llms safety

arXiv AI

Jun 9

Vision Language Model Helps Private Information De-Identification in Vision Data

arXiv:2606. 09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability.

By Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei

llms computer-vision multimodal safety

arXiv AI

Jun 9

Scaling Participation in Modular AI Systems

arXiv:2606. 07812v1 Announce Type: new Abstract: Humanity is a mosaic of multifaceted talents and needs, and any truly intelligent AI must reflect that richness.

By Shangbin Feng, Yike Wang, Weijia Shi, Luke Zettlemoyer, Yejin Choi, Yulia Tsvetkov

llms

arXiv AI

Jun 9

The AI Epistemic Deference Index: A Continuous Measure of Sycophancy

arXiv:2606. 07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.

By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt

llms benchmarks

arXiv AI

Jun 9

FormalASR: End-to-End Spoken Chinese to Formal Text

arXiv:2605. 19266v2 Announce Type: replace-cross Abstract: Automatic speech recognition (ASR) systems are typically optimized for verbatim transcription, which preserves disfluencies, filler words, and informal spoken structures that are often unsuitable for downstream writing-oriented applications.

By Wanyi Ning, Yinshang Guo, Haitao Qian, Jiyuan Cheng, Weiyuan Feng, Yufei Zhang

llms fine-tuning multimodal

arXiv AI

Jun 9

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO

arXiv:2606. 09701v1 Announce Type: cross Abstract: AI red teaming must continually adapt to evolving attackers and defenders.

By Blake Bullwinkel, Eugenia Kim, Amanda Minnich, Mark Russinovich

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 9

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale

arXiv:2604. 17406v3 Announce Type: replace Abstract: The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science.

By Xinyu Zhu, Yuzhu Cai, Zexi Liu, Cheng Wang, Fengyang Li, Wenkai Jin, Wanxu Liu, Zehao Bing, Bingyang Zheng, Jingyi Chai, Shuo Tang, Rui Ye, Yuwen Du, Xianghe Pang, Yaxin Du, Tingjia Miao, Yuzhi Zhang, Ruoxue Liao, Zhaohan Ding, Linfeng Zhang, Yanfeng Wang, Weinan E, Siheng Chen

llms agents benchmarks

arXiv AI

Jun 9

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

arXiv:2606. 08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action time.

By Xinyu Guan, Qianyang Zhao, Yuming Deng

llms rag agents fine-tuning benchmarks

arXiv AI

Jun 9

Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control

arXiv:2606. 08405v1 Announce Type: new Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures.

By Boai Sun, Wenjin Guo, Zongmin Yu, Liu Yang

llms agents reinforcement-learning multimodal safety

arXiv AI

Jun 9

AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions

arXiv:2606. 08539v1 Announce Type: new Abstract: AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per action, whether to allow, warn, block, or escalate.

By Chenglin Yang

llms rag agents

arXiv Machine Learning

Jun 9

Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction

arXiv:2601. 09285v2 Announce Type: replace Abstract: Metal-organic frameworks (MOFs) are porous crystalline materials with broad applications such as carbon capture and drug delivery, yet accurately predicting their 3D structures remains a significant challenge.

By Mianzhi Pan, JianFei Li, Peishuo Liu, Botian Wang, Yawen Ouyang, Yiming Rong, Hao Zhou, Jianbing Zhang

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 9

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation

arXiv:2601. 04498v2 Announce Type: replace Abstract: Infographics are composite visual artifacts that combine data visualizations with textual and illustrative elements to communicate information.

By Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

llms diffusion multimodal benchmarks

arXiv Machine Learning

Jun 9

The Sample Complexity of Parameter-Free Stochastic Convex Optimization

arXiv:2506. 11336v2 Announce Type: replace Abstract: We study the sample complexity of stochastic convex optimization when problem parameters such as the distance to optimality and the Lipschitz constant are unknown.

By Jared Lawrence, Ari Kalinsky, Hannah Bradfield, Yair Carmon, Oliver Hinder

llms fine-tuning

Get the daily briefing