Large language models

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

24,907 stories · RSS feed

arXiv AI

Jul 7

HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding

arXiv:2607. 04147v1 Announce Type: cross Abstract: Automated fine-grained perception of calligraphy styles--a task vital to cultural heritage preservation--remains a critical challenge for Large Vision-Language Models (LVLMs), largely constrained by existing datasets that suffer from modal mixture and flattened labels.

By Yinsheng Yao, Yan Liu, Chen Ye

llms multimodal benchmarks

arXiv AI

Jul 7

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs

arXiv:2601. 07475v2 Announce Type: replace-cross Abstract: The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference.

By Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Peng Zhang, Xindian Ma

llms efficiency benchmarks

arXiv AI

Jul 7

SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering

arXiv:2607. 04163v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering.

By Kai Tang, Jinhao You, Bohua Zhang, Yichen Guo, Yiding Sun, Dongxu Zhang, Chenxi Li, Xiande Huang, Shanghang Zhang

llms nlp multimodal benchmarks safety

arXiv AI

Jul 7

DrugAgent: Reliable Multi-Agent Integration of Conflicting Biomedical Evidence for Drug-Target Interaction Assessment

arXiv:2408. 13378v5 Announce Type: replace Abstract: Workflows in drug-target interaction (DTI) assessment require integrating heterogeneous data from predictive models, curated resources, and observations from experimental literature.

By Yoshitaka Inoue, Tianci Song, Xinling Wang, Rui Kuang, Tianfan Fu, Augustin Luna

llms rag agents nlp benchmarks

arXiv AI

Jul 7

SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models

arXiv:2607. 05365v1 Announce Type: cross Abstract: Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech.

By Thomas Thebaud, Yuzhe Wang, Hao Zhang, Sathvik Manikantan Napa Ugandhar, Ashish Hallur, Georgi Tinchev, Venkatesh Ravichandran, Laureano Moro-Velazquez

llms multimodal benchmarks

arXiv AI

Jul 7

Risk-Constrained Freshness-Aware Semantic Caching for Open-Web Retrieval-Augmented LLMs

arXiv:2607. 04281v1 Announce Type: cross Abstract: Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but most existing methods do not model the time-varying freshness of open-web evidence.

By Muhammad Mansoor, Tahir Ahmad, Yeo-Chan Yoon

llms rag benchmarks

arXiv Machine Learning

Jul 7

NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation

arXiv:2607. 04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA.

By Junjie Tang, Jun Huan, Hao Zhou, Yuhao Zhang, Lin Wang

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 7

APeB: Benchmarking Personalization Ability of Large Language Model Agents

arXiv:2607. 03162v1 Announce Type: new Abstract: LLM-powered agents struggle with personalization when users issue raw, underspecified queries.

By Garry Yang, Zizhe Chen, Xinru Chen, Yongqiang Chen, Jianxiang Wang, Deyu Zou, Linyi Ding, Jialiang Wu, Yunzhong He, Yu Gong, James Cheng, Huaixiao Tou

llms agents benchmarks

arXiv AI

Jul 7

Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding

arXiv:2607. 04383v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set.

By Zihan Zhang, Xize Cheng, Wenhao Yan, Tong Zhang, Dongjie Fu, Boyun Zhang, Yongbo He, Tao Jin

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 7

Agent Step Value: State-Transition Measurement with State-Grounded LLM Evaluators

arXiv:2607. 04419v1 Announce Type: new Abstract: Most agent evaluations collapse a multi-step trace into a final answer, a success flag, or a trajectory-level score.

By Andrew Zhang, Chengzhan Li

llms agents

arXiv AI

Jul 7

Polarity Detection of Sustainable Development Goals in News Text

arXiv:2509. 19833v4 Announce Type: replace-cross Abstract: The United Nations' Sustainable Development Goals (SDGs) provide a globally recognised framework for addressing major societal, environmental, and economic challenges.

By Andrea Cadeddu, Alessandro Chessa, Vincenzo De Leo, Gianni Fenu, Francesco Osborne, Diego Reforgiato Recupero, Angelo Salatino, Luca Secchi

llms nlp fine-tuning benchmarks

arXiv AI

Jul 7

RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents

arXiv:2607. 04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks.

By Qiang Liu, Taian Guo, Ruizhi Qiao, Xing Sun

llms agents reinforcement-learning efficiency benchmarks safety

arXiv AI

Jul 7

HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation

arXiv:2607. 04329v1 Announce Type: new Abstract: Large language models increasingly operate in settings where humans are active collaborators rather than passive task providers.

By Yaozu Wu, Wei-Chieh Huang, Jizhou Guo, Dongyuan Li, Renhe Jiang, Henry Peng Zou, Chunyu Miao, Shanghao Li, Weizhi Zhang, WeiWei Ye, Yankai Chen, Meng Zhang, Xue Liu, Philip S. Yu

llms agents benchmarks safety

arXiv AI

Jul 7

Shortcut Learning in Legal Judgment Prediction: Empirical Evidence from the UK Employment Tribunal

arXiv:2607. 04261v1 Announce Type: new Abstract: Current Legal Judgment Prediction (LJP) is constrained by its reliance on post-hoc judicial materials, increasing the likelihood that models perform retrospective classification rather than true forecasting.

By Joe Watson, Joana Ribeiro de Faria, Marcus Tomalin, M{\aa}ns Magnusson, Huiyuan Xie, Hao Tian Yeung, Felix Steffek

llms

arXiv AI

Jul 7

Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents

arXiv:2607. 04528v1 Announce Type: new Abstract: Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees, which actions it can take, which failures are repaired, which states are verified, and which evidence is logged.

By Haiwen Yi, Xinyuan Song

llms agents efficiency benchmarks safety

arXiv AI

Jul 7

Knowledge-Centric Information Systems

arXiv:2607. 02609v1 Announce Type: cross Abstract: For decades, data engineering has developed mature architectural principles for integrating, governing, validating, cataloging, and serving organizational data.

By Mariano Garralda-Barrio

llms agents data-engineering

arXiv AI

Jul 7

Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5

arXiv:2607. 04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.

By Lyndon Drake (University of Oxford), Zandi Eberstadt (University of Oxford)

llms fine-tuning

arXiv AI

Jul 7

Multi-Turn On-Policy Distillation with Prefix Replay

arXiv:2607. 04763v1 Announce Type: cross Abstract: We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories.

By Baohao Liao, Hanze Dong, Christof Monz, Xinxing Xu, Li Dong, Furu Wei

llms agents efficiency

arXiv AI

Jul 7

LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2

arXiv:2508. 16181v2 Announce Type: replace-cross Abstract: Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across independently developed system models.

By Zirui Li, Stephan Husung, Haoze Wang

llms safety

arXiv AI

Jul 7

NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO

arXiv:2607. 03957v1 Announce Type: cross Abstract: Language models can reach the right normative verdict for the wrong reason.

By Xinqi Zhang

llms fine-tuning benchmarks

Get the daily briefing