Large language models

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

21,000 stories · RSS feed

arXiv AI

Jul 20

GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis

arXiv:2607. 15280v1 Announce Type: new Abstract: Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering.

By Shaoting Tan, Ning Liu, Yuntao Du, Shuyue Wei, Wu Shuai, Qian Li, Yanyu Xu, Wei Zhang, Lizhen Cui, Haitao Yuan

llms agents efficiency

arXiv AI

Jul 20

Process Reward Informed Tree Rollout for Effective Multi-Turn RL

arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.

By Xintong Li, Sha Li, Yuwei Zhang, Changlong Yu, Rongmei Lin, Hongye Jin, Shuyi Guan, Xin Liu, Linwei Li, Qingyu Yin, Jingbo Shang

llms agents reinforcement-learning

arXiv Machine Learning

Jul 20

Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention

arXiv:2607. 15449v1 Announce Type: new Abstract: Using the language of Wilsonian renormalization group theory (RG), we treat the Transformer's attention mechanism as a perturbation of the trained MLP residual-stack fixed point and ask whether it constitutes a relevant, marginal, or irrelevant operator.

By Parviz Haggi-Mani, Irina Rish

llms

arXiv Machine Learning

Jul 20

PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization

arXiv:2607. 16184v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) is a popular class of large language models (LLMs), offering high efficiency and accuracy.

By Yuchen Yang, Yifan Zhao, Anisha Dasgupta, Sasa Misailovic

llms efficiency

arXiv AI

Jul 20

Ask Twice, Look Twice: Prompt Echoing Resolves the Question-First Paradox in Vision-Language Models

arXiv:2607. 15565v1 Announce Type: cross Abstract: Where should the question go in a vision-language model (VLM) prompt: before the image or after it?

By Rakshanda Hassan Abhinandan, John Galeotti, Deva Ramanan, Gautam Rajendrakumar Gare

llms nlp fine-tuning multimodal benchmarks

arXiv AI

Jul 20

Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.

By Bo-An Chang, Yu-Chih Chen

llms diffusion nlp reinforcement-learning multimodal benchmarks safety

arXiv AI

Jul 20

RL-Struct: A Lightweight Reinforcement Learning Framework for Reliable Structured Output in LLMs

arXiv:2512. 00319v3 Announce Type: replace Abstract: The Structure Gap between probabilistic LLM generation and deterministic schema requirements hinders automated workflows.

By Ruike Hu, Shulei Wu

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Jul 20

ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Language

arXiv:2607. 15607v1 Announce Type: new Abstract: Hallucinations and artificial text in LLM-generated outputs often appear as distributional deviations between prompt and response hidden-state distributions.

By Sergey Zakharov, Rodion Oblovatny, Alexey Zaytsev

llms benchmarks safety

arXiv AI

Jul 20

Scalable LLM Agent Tool Access in the Cloud

arXiv:2607. 15593v1 Announce Type: cross Abstract: LLM agents increasingly rely on tool calling to act on external systems, and the Model Context Protocol (MCP) has quickly become its de facto interface.

By Mingxin Li, Enge Song, Yueshang Zuo, Xiaodong Liu, Rong Wen, Qiang Fu, Gianni Antichi, Jian He, Jing Tie, Zhou Shao, Xiaobo Xue, Xiong Xiao, Luyao Zhong, Shaokai Zhang, Jiangu Zhao, Jianyuan Lu, Shize Zhang, Xiaoqing Sun, Changgang Zheng, Zihao Fan, Haonan Li, Tian Pan, Xiaomin Wu, Yang Song, Xing Li, Biao Lyu, Meng Li, Haipeng Dai, Guihai Chen, Shunmin Zhu

llms agents efficiency

arXiv AI

Jul 20

IMBench: A Benchmark for Intuitive Robotic Manipulation

arXiv:2607. 15641v1 Announce Type: cross Abstract: Humans combine reasoning and motor control to solve complex manipulation tasks under diverse constraints.

By Anurag Maurya, Sukhvansh Jain, Prajwal Avhad, Gautham Balachandran, Ziyi Zhou, Atharva Kshirsagar, Satyam Singh, Bowen Li. Rishabh Mukund, Ritul Singh, Jatin Vira, Suvonil Chatterjee, Devesh K. Jha

llms agents robotics multimodal benchmarks

arXiv AI

Jul 20

MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

arXiv:2607. 15592v1 Announce Type: new Abstract: Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues.

By Xu Hou, Meiyu Liang, Wei Huang, Yawen Li, Zhe Xue, Wu Liu, Guanhua Ye, Lei Shi, Kangkang Lu

llms diffusion multimodal benchmarks safety

arXiv AI

Jul 20

Evaluating Open-Weight LLMs for Generating Structured Threat Information for Autonomous Vehicle Vulnerabilities

arXiv:2607. 16175v1 Announce Type: cross Abstract: Connected and Autonomous Vehicles (CAVs) rely on interconnected software and hardware components, including sensors, Electronic Control Units, in-vehicle infotainment systems, and telematics units, where vulnerabilities can compromise assets, users, and vehicle operations.

By Md Erfan, Ahmed Ryan, Md Kamal Hossain Chowdhury, Md Rayhanur Rahman

llms agents

arXiv AI

Jul 20

NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning

arXiv:2607. 15776v1 Announce Type: new Abstract: OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics.

By Hui Yang, Jiaoyan Chen, Yiping Song, Renate Schmidt, Wen Zhang

llms rag

arXiv AI

Jul 20

DECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods

arXiv:2607. 15879v1 Announce Type: cross Abstract: Much empirical legal research depends on translating unstructured text into structured variables.

By Jens Frankenreiter

llms benchmarks

arXiv AI

Jul 20

CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data

arXiv:2607. 16122v1 Announce Type: new Abstract: Evaluations should do more than measure a models current performance.

By Vipul Gupta, Zihao Wang, Razvan-Gabriel Dumitru, MohammadHossein Rezaei, Aakash Sabharwal, Yunzhong He

llms fine-tuning benchmarks

arXiv AI

Jul 20

Cura 1T: Specialized Model for Agentic Healthcare

arXiv:2607. 15314v1 Announce Type: new Abstract: Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized LLMs that cover these use cases together remain limited.

By actAVA AI, :, Haolin Chen, Leon Qi, Steve Brown, Deon Metelski, Tao Xia, Joonyul Lee, Qixuan Wang, Kevin Riley, Frank Wang, Weiran Yao

llms agents benchmarks

arXiv AI

Jul 20

DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction

arXiv:2607. 16012v1 Announce Type: cross Abstract: Multi-Task Learning (MTL) in robotics perception systems supports comprehensive 3D spatial scene understanding by integrating semantic segmentation and depth estimation.

By Jehun Kang, Jungha Wang, Youngjun Hwang, David Hyunchul Shim

llms computer-vision robotics efficiency benchmarks

arXiv AI

Jul 20

Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought Length

arXiv:2512. 07019v3 Announce Type: replace-cross Abstract: The proliferation of Large Language Models (LLMs) necessitates valid evaluation methods to provide guidance for both downstream applications and actionable future improvements.

By Zhiyu Xu, Jia Liu, Yixin Wang, Yuqi Gu

llms benchmarks

arXiv AI

Jul 20

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

arXiv:2607. 15434v1 Announce Type: cross Abstract: Multi-agent systems routinely place one AI agent in authority over another.

By Jasmine Brazilek, Maheep Chaudhary, Zoe Lu, Miles Tidmarsh

llms agents benchmarks

arXiv AI

Jul 20

Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction

arXiv:2607. 15281v1 Announce Type: new Abstract: Causal and intervention-based question answering is fundamental to advancing large language models (LLMs) toward reasoning beyond surface-level correlations and understanding underlying causal mechanisms.

By Su Lan, Xuefei Yin, Yanming Zhu, Alan Wee-Chung Liew

llms nlp benchmarks

Get the daily briefing