Large language models

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

31,367 stories · RSS feed

arXiv Machine Learning

Sep 22

Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning

The paper introduces Strategy Accumulation and Guided Execution (SAGE), a two-stage framework that makes automated fine-tuning of large language models cumulative. In the first stage, a multi-agent pipeline uses Monte Carlo Tree Search to explore training strategies while a Distillation Agent records task-specific insights and cross-task confidence scores into a structured repository. In the second stage, SAGE retrieves relevant experience from this repository to guide training on new tasks, achieving a 12.4‑percentage‑point improvement over a baseline pipeline without accumulated experience on nine unseen tasks.

By Haoran Zhao, Wei Du, Dingwen Yang, Jixuan Huang, Junlin Shang, Lingyong Fang, Ya Guo, Tao Gui, Qi Zhang, Xuanjing Huang

llms agents fine-tuning efficiency

arXiv Machine Learning

Sep 22

Preserving Geometric Integrity in Graph Prompting via Measure-Constrained Optimal Transport

arXiv:2609.23547v1 Announce Type: new Abstract: Graph prompt learning enables parameter-efficient adaptation of frozen Graph Neural Networks to downstream tasks through lightweight prompt parameters....

By Xiangyu Wang, Shuo Wang, Ruiyi Fang, Zhao Kang

llms

arXiv Machine Learning

Sep 22

Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning

arXiv:2609.23775v1 Announce Type: new Abstract: Obtaining the optimal action-value function in Markov decision processes is computationally intensive in large state--action spaces. In this study, we...

By Suman Banerjee, Hiroyasu Tsukamoto

llms reinforcement-learning

arXiv Machine Learning

Sep 22

Real-time Generalizable Heart Valve Mechanics for Clinical Disease Assessment via a Physics-Conditioned Neural Operator

arXiv:2609.23826v1 Announce Type: new Abstract: Mitral regurgitation is the most common heart valve disorder worldwide, affecting over 2% of the global population, rising to at least 10% in adults ov...

By Shawn Koohy, Wensi Wu, Matthew A Jolley, Paris Perdikaris

llms

arXiv Machine Learning

Sep 22

SPeaR: Test-Time Adaptation with Steering Primitives for Realigning Representations

arXiv:2609.24111v1 Announce Type: new Abstract: Test-time adaptation (TTA) addresses distribution shift using only unlabeled test data. Existing methods typically adapt pretrained models by updating...

By Muhammad Sudipto Siam Dip, Ali Etemad

llms

arXiv Machine Learning

Sep 22

Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation

arXiv:2609.24146v1 Announce Type: new Abstract: Language model agents are increasingly used to simulate social interaction, and the resulting transcripts read as though the agents understand one anot...

By Cong Li, Cheng Chen, Thomas Fung, Alex Rossi, Yi Li

llms agents

arXiv Machine Learning

Sep 22

H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache

arXiv:2609.24197v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates large language model inference by having a lightweight draft model predict future tokens for verification b...

By Weifan Jiang, Krishna Teja Chitty-Venkata, Megan Flynn, Reed Meyerson, Zhenting Qi, Tianyu Wu, Eldar Kurtic, Minlan Yu, Alexandre Marques

llms diffusion efficiency

arXiv Machine Learning

Sep 22

SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration

arXiv:2609.24303v1 Announce Type: new Abstract: Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident t...

By Linhan Luo, Lequan Lin, Dai Shi, Feng Chen, Jos\'e Miguel Hern\'andez-Lobato, Junbin Gao

llms safety

arXiv Machine Learning

Sep 22

A Distributional Optimisation Perspective on Combining Models in Deep Learning

arXiv:2609.24328v1 Announce Type: new Abstract: Combining predictions from different models can improve performance at machine learning tasks, but the training of the individual models and the rule u...

By Congye Wang, Yan Lin, Zheyang Shen, Matthew A. Fisher, Chris. J. Oates

llms fine-tuning benchmarks

arXiv Machine Learning

Sep 22

Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse

arXiv:2609.24338v1 Announce Type: new Abstract: An Intraoperative Hypotension (IOH) event is a frequent complication during administration of general anaesthesia with serious downstream consequences,...

By Rithin Nagaraj, Sudiksha Chindula, Bhaskarjyoti Das

llms efficiency

arXiv Machine Learning

Sep 22

Prescriptive SVD-Inspired Attention via Spectral Energy Retention

arXiv:2609.24370v1 Announce Type: new Abstract: Self-attention is central to modern Transformer architectures, but its dense dot-product formulation makes it difficult to identify which internal dire...

By Vasileios Arampatzakis, Vasileios Sevetlidis, George Pavlidis

llms efficiency safety

arXiv Machine Learning

Sep 22

Prior-Amortized In-Context Bayesian Inference for Generalized Linear Mixed-Effects Models

arXiv:2609.24422v1 Announce Type: new Abstract: Hierarchical data is ubiquitous in the empirical sciences and is most commonly analyzed with generalized linear mixed-effects models (GLMMs). Bayesian...

By Alex Kipnis, Marcel Binz, Eric Schulz

llms benchmarks

arXiv Machine Learning

Sep 22

A Temporal Knowledge Graph for Music Festival Lineup Forecasting

arXiv:2609.24467v1 Announce Type: new Abstract: Music festival lineups emerge from complex relationships among artists, genres, releases, labels, and past performances, making the prediction of futur...

By Julia Gastinger, Thilo Dieing, Christian Meilicke, Heiner Stuckenschmidt

llms benchmarks

arXiv Machine Learning

Sep 22

Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction

arXiv:2609.24579v1 Announce Type: new Abstract: Event logs arise in a wide range of real-world processes, capturing not only event activities and timestamps but also multi-modal contextual informatio...

By Fabian Spaeh, Jingxing Fang, Shandian Zhe, Bin Shen

llms multimodal

arXiv Machine Learning

Sep 22

LoRA-generating hypernetworks for efficient on-device LLM generative personalization

arXiv:2609.24979v1 Announce Type: new Abstract: On-device large language models (`LLMs'), e.g. running on mobile phones, are ripe for improvement via personalization. The limited compute resources of...

By Sean Augenstein, Li Ding, Jihwan Lee, Keith Rush, Andrey Zhmoginov

llms fine-tuning

arXiv Machine Learning

Sep 22

AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation

arXiv:2609.22100v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce...

By Artem Sakhno, Grigorii Davydenko, Omar Zoloev, Julia Belikova, Andrey Savchenko, Maksim Makarenko

llms rag efficiency benchmarks

arXiv Machine Learning

Sep 22

Evaluation Awareness Shifts from Format to Context with Model Scale

arXiv:2609.22119v1 Announce Type: cross Abstract: Evaluation awareness poses an unprecedented threat to model evaluation, but the mechanisms by which models detect it remain unknown. This study focus...

By Navraj Singh, Maheep Chaudhary

llms

arXiv Machine Learning

Sep 22

Correlation-Aware Structured Pruning for Large Language Models

arXiv:2609.22131v1 Announce Type: cross Abstract: Structured pruning is a promising approach for reducing the substantial inference costs of Large Language Models (LLMs) while maintaining hardware ef...

By Sicheng Xu, Hao Shi, Wei Zhang, Haoran Pang, Zhenyu Ming, Hao Wu, Zhongyi Huang, Xin Yao, Gong Zhang

llms efficiency

arXiv Machine Learning

Sep 22

Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantization

arXiv:2609.22149v1 Announce Type: cross Abstract: Multimodal synthetic datasets combine structured attributes with free text, but are often evaluated separately. Such metrics can remain high after ta...

By Yefeng Yuan, Zhan Shi, Liang Cheng, Yuhong Liu

llms rag efficiency multimodal

arXiv Machine Learning

Sep 22

ECP-Bench: Benchmarking and Learning Entertainment Content Promotion with Foundation Models

arXiv:2609.22150v1 Announce Type: cross Abstract: Content promotion spans a broad set of skills, from understanding content to forecasting its market reception. However, LLMs' ability to support such...

By Hyomin Kim, Bowen Chen, Jin Huang, Zhao Wang, Qiaozhu Mei, Shingo Takamatsu

llms fine-tuning benchmarks

Get the daily briefing