Large language models

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

31,598 stories · RSS feed

arXiv AI

Sep 21

How do LLMs Compute Verbal Confidence

arXiv:2603.17839v4 Announce Type: replace-cross Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from...

By Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Veli\v{c}kovi\'c

llms benchmarks

arXiv AI

Sep 21

How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models

arXiv:2604.27167v3 Announce Type: replace-cross Abstract: On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, loc...

By Paraskevas V. Lekeas, Giorgos Stamatopoulos

llms agents

arXiv AI

Sep 21

Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning

arXiv:2607.08837v4 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...

By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong

llms reinforcement-learning robotics multimodal

arXiv Machine Learning

Sep 21

Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks

arXiv:2609.21039v1 Announce Type: new Abstract: A pervasive structural pattern in modern deep learning is the linear factorization block: a submodule of the form $W = BA$ in which two parameter matri...

By Emanuele Zangrando, Marco Sutti, Francesco Tudisco

llms fine-tuning

arXiv Machine Learning

Sep 21

TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching

arXiv:2609.21172v1 Announce Type: new Abstract: Large language models (LLMs) are moving onto mobile devices for increasingly diverse workloads over text, images, video, and audio. These applications...

By Zhihao Shu, Md Musfiqur Rahman Sanim, Jie Hu, Kun Yuan, Minghai Qin, Gagan Agrawal, Wei Niu

llms efficiency

arXiv Machine Learning

Sep 21

Probabilistic Forecasting of Business Process Executions with Neural Temporal Point Processes

arXiv:2609.21382v1 Announce Type: new Abstract: Operators of service-based systems act on forecasts of how a running execution will continue, and such a forecast is actionable only if its reliability...

By Jiaxin Yuan, Daniela Grigori, Han van der Aa

llms

arXiv Machine Learning

Sep 21

Understanding LLM Quantization through Activation-Guided Compensation and Orthogonal Residuals

arXiv:2609.21450v1 Announce Type: new Abstract: Post-training weight-activation quantization reduces the memory and inference costs of large language models, but aggressive W4A4 quantization remains...

By Yamato Narita, Issei Sato

llms efficiency

arXiv Machine Learning

Sep 21

MACE: Memory-Agent Co-Evolution with Adaptive Memory Graphs for Multi-Agent Systems

arXiv:2609.21533v1 Announce Type: new Abstract: LLM-based multi-agent systems generate collaboration traces that record how agents plan tasks, verify intermediate results, and repair failures. Reusin...

By Kairui Yang, Minghao An, Xunkai Li, Ziheng Yi, Zekai Chen, Guangyuan He, Rong-Hua Li

llms agents benchmarks

arXiv Machine Learning

Sep 21

ExpBoN: Exponential-Noise Best-of-$n$ for Efficient Test-Time LLM Alignment

arXiv:2609.21899v1 Announce Type: new Abstract: Best-of-$n$ (BoN) sampling is a simple yet effective inference-time alignment method, but hard maximization provides only coarse control over the trade...

By Yanxiao Liu, Sicheng Wan, Deniz G\"und\"uz

llms benchmarks safety

arXiv Machine Learning

Sep 21

Joint Remaining Useful Life Prediction and Capacity Estimation of Lithium-Ion Batteries Using Partial-Charging Data

arXiv:2609.21932v1 Announce Type: new Abstract: Joint remaining useful life (RUL) prediction and capacity estimation require representations of both gradual degradation and recent battery behavior. T...

By Khoa Tran, Ho-Si-Hung Nguyen, Phone Wai Yan Moe, Hung-Cuong Trinh, Thi-Hoang-Giang Tran

llms

arXiv Machine Learning

Sep 21

Complex Problem Solving in Large Language Models: A Statistical Control Survey and Diagnostic Framework

arXiv:2609.20973v1 Announce Type: cross Abstract: Complex problem solving (CPS) with large language models (LLMs) is often framed as a matter of stronger reasoning or longer generation. Yet early-ste...

By Jiazhang Cai, Tao Wang, Ruidong Zhang, Siyuan Li, Terry Ma, Luyang Fang, Haoran Lu, Huimin Cheng, Yingchuan Zhang, Shushan Wu, Rui Xie, Lin Tang, Chao Huang, Rongjie Liu, Ziyu Liu, Meizhi Yu, Yongkai Chen, Yifan Zhou, Zeliang Sun, Chang Liu, Zhen Xiang, Wei Xiao, Zixin Rao, Xinyi Liu, Yutong Hu, Mengrui Zhang, Jing Zhang, Weidi Luo, Jincheng Yu, Zhengliang Liu, Weihang You, Hanqi Jiang, Yi Pan, Junhao Chen, Xinliang Li, Tianming Liu, Wenxuan Zhong, Ping Ma

llms safety

arXiv Machine Learning

Sep 21

How Many Humans Is a Judge Panel Worth?

arXiv:2609.21277v1 Announce Type: cross Abstract: How many human judgments does a panel of language models represent? The answer depends on what is matched. We audit categorical judge panels against...

By Chao Li, Yingying Yu, Yunfeng Li

llms

arXiv Machine Learning

Sep 21

Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Models

arXiv:2609.21363v1 Announce Type: cross Abstract: Multimodal large reasoning models (MLRMs) have demonstrated remarkable capabilities in complex visual understanding. However, this very power introdu...

By Yining Wang, Xi Li, Mi Zhang, Xiaohan Zhang, Xiaoyu You, Zhenxing Qian, Mi Wen

llms diffusion multimodal safety

arXiv Machine Learning

Sep 21

Prediction Dynamics in Depth-Recurrent Language Models

arXiv:2609.21383v1 Announce Type: cross Abstract: Depth-recurrent language models refine predictions through repeated latent updates. Why can intermediate answers agree with the endpoint while their...

By Xinyue Luo, Fei Yu

llms

arXiv Machine Learning

Sep 21

Fidel-TS: A High-Fidelity Multimodal Benchmark for Time Series Forecasting

arXiv:2509.24789v5 Announce Type: replace Abstract: The evaluation of time series forecasting models is hindered by a lack of high-quality benchmarks, leading to overestimated assessments of progress...

By Zhijian Xu, Wanxu Cai, Xilin Dai, Zhaorong Deng, Qiang Xu

llms multimodal benchmarks