Large language models

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

18,779 stories · RSS feed

arXiv AI

Jul 28

The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards

arXiv:2607. 24063v1 Announce Type: new Abstract: On standard factuality tasks, frontier models now cluster near the top of the scale.

By Keyu Li, Jin Gao, Dequan Wang

llms agents nlp benchmarks safety

arXiv AI

Jul 28

Falsifiable Commitment Planning for Self-Correcting Web Agents

arXiv:2607. 24167v1 Announce Type: new Abstract: Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, or plan assumption no longer supports the user instruction.

By Guangyi Liu, Huan Zhao, Quanming Yao

llms agents

arXiv AI

Jul 28

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

arXiv:2607. 24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforcement learning (RL) provides only sparse supervision.

By Junlin Liu, Jiangwang Chen, Zixin Song, Shuaiyu Zhou, Chunji Lv, Hank Wu, Kailin Jiang, Jinyang Wu, Bohan Yu, Chenxi Zhou

llms agents reinforcement-learning efficiency benchmarks

arXiv AI

Jul 28

MegaSlide-DiT: Memory-Centric Adaptation and Deformable Local Attention for Efficient Video Diffusion

arXiv:2607. 22696v1 Announce Type: cross Abstract: High-resolution video diffusion models built on Diffusion Transformers (DiTs) deliver strong fidelity but quickly exhaust the memory budget of a single workstation.

By Jiacheng Liu, Jason Liu

llms diffusion

arXiv AI

Jul 28

Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model

arXiv:2607. 22704v1 Announce Type: cross Abstract: Nuclear fusion has made significant progress in recent years and is expected to become one of the most important pathways to addressing global energy challenges.

By Xiao Wang, Hao Si, Qiang Chen, Yu-Xiang Zhang, Beihe Zhang, Jianhua Yang, Qingquan Yang, Dengdi Sun, Wanli Lyu, Guosheng Xu, Jin Tang

llms

arXiv AI

Jul 28

DAMamba-UNet3D: A Parameter-Efficient Mamba State Space U-Net with Dynamic Adaptive Scan for 3D Medical Image Segmentation

arXiv:2607. 22718v1 Announce Type: cross Abstract: We propose parameter-efficient SSM-based U-Net architectures for 3D medical image segmentation.

By Mohammad Arafat Hussain, Ellen Grant, Yangming Ou

llms computer-vision

arXiv AI

Jul 28

An Interactive Vision Language Platform for Cognitive Remediation in Schizophrenia

arXiv:2607. 22721v1 Announce Type: cross Abstract: Cognitive remediation tasks often require patients to perform structured actions involving object manipulation and sequential reasoning.

By Nassira Ait Mehdi, Milissa Temmam, Slimane Larabi

llms robotics fine-tuning multimodal

arXiv AI

Jul 28

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.

By Yunting Song, Matthew Watson, Peter Grabowski, Jun Qin

llms reinforcement-learning benchmarks safety data-engineering

arXiv AI

Jul 28

Spectral Dynamics of Semantic Drift in Clinical Multi-Agent Language Model Networks

arXiv:2607. 22758v1 Announce Type: cross Abstract: The integration of iterative LLMs within multi-agent diagnostic frameworks requires a rigorous quantitative reevaluation of underlying communication topologies.

By Amritesh Banerjee

llms rag agents diffusion safety

arXiv AI

Jul 28

Hierarchical Grading in Large Language Models

arXiv:2607. 22757v1 Announce Type: cross Abstract: We introduce Graded Large Language Models (GLLMs), an algebraic framework that equips the representation space of a transformer with a grading and propagates the induced weighted scalar action through embeddings, self-attention, and the training objective.

By T. Shaska

llms rag

arXiv AI

Jul 28

LithoFormer: A Robust Framework for Stratigraphic Inference via Transformers

arXiv:2607. 22804v1 Announce Type: cross Abstract: Accurate geological characterization of subsurface reservoirs from well log data is essential to support projects such as carbon capture and storage (CCS), geothermal development, and extraction of natural resources.

By Shwetha Salimath, Francesca Bugiotti, Sylvain Wlodarczyk, Sohaib Ouzineb

llms rag

arXiv AI

Jul 28

Physically Verifiable Evidence and LLM-Based Reporting for Bearing Fault Diagnosis

arXiv:2607. 22797v1 Announce Type: cross Abstract: Trustworthy deployment of AI-based diagnosis in safety-critical mechanical systems hinges on validation: whether a prediction can be checked against physical reality before it is acted upon.

By Yuntong Chen, Jianyu Liu, Guobin Zhao, Ziang Wang, Chao Chen, Ju Huang, Xitian Tian, Lijiang Huang

llms fine-tuning safety

arXiv AI

Jul 28

Agentic Autoresearch for CT Reconstruction

arXiv:2607. 22824v1 Announce Type: cross Abstract: Comparing CT reconstruction methods fairly is labor-intensive and largely manual, and many benchmarks use idealized data.

By Andreas Maier, Lucas Kachelriess, Siming Bayer, Yixing Huang, Yan Xia, Amber Simpson, Moritz Zaiss

llms agents benchmarks

arXiv AI

Jul 28

Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

arXiv:2607. 22864v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably.

By Patrick Rim, Tom Long, Ekta Prashnani, Ruth Rosenholtz, Ben Boudaoud, Peter Xenopoulos, Alex Wong, Joohwan Kim, Jae-Hyun Jung

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jul 28

Language-Routed RAG and Direct Option Scoring for Multilingual Financial QA: DS@GT at FinMMEval

arXiv:2607. 22841v1 Announce Type: cross Abstract: We present DS@GT's submission to FinMMEval 2026 Task 1, a multilingual financial exam question answering benchmark spanning English, Spanish, Greek, Chinese, and Hindi.

By Justice Ayela, Kabir Sahni

llms rag nlp benchmarks

arXiv AI

Jul 28

Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop

arXiv:2607. 23002v1 Announce Type: cross Abstract: Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified.

By Jeff Otterson (W. P. Carey School of Business, Arizona State University)

llms safety

arXiv AI

Jul 28

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy

arXiv:2607. 23006v1 Announce Type: cross Abstract: Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the supporting evidence within those papers.

By Xinyan Zhong, Yuwei Shi, Yuqi Wei, Chen Shen, Tianhang Zhou, Zhenghao Wu

llms rag agents nlp benchmarks

arXiv AI

Jul 28

Traceable LLM Reasoning for Fake-Order Fraud Detection

arXiv:2607. 23075v1 Announce Type: cross Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability.

By Siqi You, Bingsong Xu, Zhixian Zheng, Xinjian Peng, Yang Xie, Ying Wang, Jiarong Xu

llms reinforcement-learning fine-tuning safety

arXiv AI

Jul 28

Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models

arXiv:2607. 23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference.

By Dhruvil S, Fenil Sojitra, Ravirajsinh Chauhan

llms fine-tuning safety

arXiv AI

Jul 28

Novel Claim or D\'ej\`a Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking

arXiv:2607. 23514v1 Announce Type: cross Abstract: Multimodal automated fact-checking (MAFC) verifies claims by retrieving and reasoning over external evidence.

By Haorui He, Xinwen Chen, Dacheng Wen, Reynold Cheng, Francis C. M. Lau, Yupeng Li

llms multimodal benchmarks

Get the daily briefing