Large language models

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

24,369 stories · RSS feed

arXiv Machine Learning

Jul 8

A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models

arXiv:2607. 05615v1 Announce Type: new Abstract: Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering signal at every generated token, incurring constant per-token perturbation that risks degrading fluency.

By Nima Eshraghi, Lovedeep Gondara, Yuqing Huang, Sagarika Suresh, Leizer Teran, Jithin Pradeep, Xiaotong Xu, Fanny Chevalier

llms reinforcement-learning fine-tuning

arXiv AI

Jul 8

Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation

arXiv:2607. 05554v1 Announce Type: cross Abstract: Survey-style evaluations of large language models often treat a prompted response as a measure of a model's values or beliefs.

By Sadia Kamal, Arefa Patwary, Anthony Marchiafava, Atriya Sen, Sagnik Ray Choudhury

llms benchmarks

arXiv AI

Jul 8

CANONIC: Governance Is Compilation

arXiv:2607. 05410v1 Announce Type: cross Abstract: We present CANONIC: governed intelligence that compiles digital artifacts into an evidence ledger at scale.

By Dexter Hadley

llms benchmarks

arXiv AI

Jul 8

i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler

arXiv:2607. 05888v1 Announce Type: cross Abstract: i-EXAM is a planning-powered tool that helps system administrators to create security profiles of complex networks and perform what-if analyses to identify network hardening strategies.

By Rakesh Podder, Wadia Ganim, Sarath Sreedharan, Indrajit Ray, Indrakshi Ray

llms

arXiv AI

Jul 8

FirstResearch: Auditable Question Formation for LLM Scientific Discovery Agents

arXiv:2607. 05682v1 Announce Type: new Abstract: LLM systems for scientific discovery increasingly assist with ideation, literature synthesis, experiment planning, and report generation, but the first research question they propose can remain difficult to audit: it may sound plausible without exposing the mechanism, falsifier, or assumption that a scientist should inspect.

By Yufeng Wang

llms agents benchmarks

arXiv Machine Learning

Jul 8

Energy-Efficient GPU DVFS for Fine-Tuning of SLMs on Resource-constrained Embedded Devices

arXiv:2607. 05933v1 Announce Type: cross Abstract: Dynamic Voltage Frequency Scaling (DVFS) on resource-constrained embedded GPU platforms is essential for energy-efficient small language model (SLM) fine-tuning, as privacy- and personalization-driven adaptation increasingly requires local execution and involves repeated forward-backward optimization over many mini-batches, making it substantially more time- and energy-intensive than single-pass inference.

By Jurn-Gyu Park, Sanzhar Zholdybayev, Aidar Amangeldi, Ademi Zhanuzakova

llms fine-tuning benchmarks safety

arXiv AI

Jul 8

EvalLoop: A Methodology for Evaluation-Driven Iterative Improvement of Business AI Systems

arXiv:2607. 05638v1 Announce Type: cross Abstract: Teams deploying large language models in business contexts need evaluation systems, yet most treat evaluation as static model selection: run benchmarks, rank models, deploy the winner.

By Kenneth Benavides, Josh Fleischer, Danti Chen

llms agents benchmarks safety

arXiv AI

Jul 8

Harrison.Rad 1.5 Technical Report: A radiology foundation model that can draft reports from images, priors and clinical context

arXiv:2607. 05880v1 Announce Type: cross Abstract: Imaging demand is growing faster than the radiology workforce can expand, and reporting backlogs cannot be resolved through training and recruitment alone.

By Suneeta Mall, Vladimir Nekrasov, Ashnil Kumar, Sajith Karunasena, Aiden Nibali, Alix Bird, Mateo Diaz Shine, Jarrel Seah

llms fine-tuning multimodal

arXiv Machine Learning

Jul 8

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.

By Chenyu Zhou

llms reinforcement-learning

arXiv AI

Jul 8

Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges

arXiv:2605. 19723v2 Announce Type: replace-cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial intelligence systems.

By Husnain Amjad, Raja Khurram Shahzad, Aamir Shahzad, Mehwish Fatima

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 8

A semantic mutation metric for metamorphic relation adequacy in scientific computing programs

arXiv:2605. 17437v2 Announce Type: replace-cross Abstract: Context.

By Meng Li (School of Computing, University of South China, Hengyang, China, Hunan Engineering Research Center of Software Evaluation and Testing for Intellectual Equipment, Hengyang, China, CNNC Key Laboratory on High Trusted Computing, Hengyang, China), Xiaohua Yang (School of Computing, University of South China, Hengyang, China, Hunan Engineering Research Center of Software Evaluation and Testing for Intellectual Equipment, Hengyang, China, CNNC Key Laboratory on High Trusted Computing, Hengyang, China), Jie Liu (School of Computing, University of South China, Hengyang, China, Hunan Engineering Research Center of Software Evaluation and Testing for Intellectual Equipment, Hengyang, China, CNNC Key Laboratory on High Trusted Computing, Hengyang, China), Shiyu Yan (School of Computing, University of South China, Hengyang, China, Hunan Engineering Research Center of Software Evaluation and Testing for Intellectual Equipment, Hengyang, China, CNNC Key Laboratory on High Trusted Computing, Hengyang, China)

llms benchmarks

arXiv Machine Learning

Jul 8

Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates

arXiv:2604. 04738v2 Announce Type: replace-cross Abstract: Fine-tuning is the dominant paradigm for adapting large machine learning models, yet current deployment pipelines provide no way to verify how a released model was updated.

By Zhenhang Shang, Yingzhe Yu, Kani Chen

llms fine-tuning efficiency benchmarks

arXiv AI

Jul 8

EcoVision: AI-Powered Drone Imaging for Salt Marsh Vegetation Monitoring and Dominance Mapping

arXiv:2607. 06105v1 Announce Type: cross Abstract: High-resolution RGB imagery acquired from low-altitude UAV surveys was processed through a modular pipeline incorporating transformer-based semantic segmentation, connected-component vegetation extraction, fine-grained species classification using a ConvNeXt architecture, and grid-based dominance scoring at 2x2m resolution.

By Innocent Onyenonachi, Peter J. Lawerance, Nadia Kanwal

llms computer-vision robotics

arXiv AI

Jul 8

Universal Algorithm-Implicit Learning

arXiv:2602. 14761v2 Announce Type: replace-cross Abstract: Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability.

By Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner

llms rag nlp multimodal benchmarks

arXiv AI

Jul 8

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.

By Kai Ruan, Zihe Huang, Ziqi Zhou, Qianshan Wei, Xuan Wang, Hao Sun

llms agents

arXiv AI

Jul 8

Learning from Execution: Self-Evolving Memory for Private-Library Code Generation

arXiv:2604. 24222v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved strong performance on general code generation, but their effectiveness drops sharply in enterprise settings where software development relies on internal private libraries absent from public pre-training corpora.

By Mofei Li, Taozhi Chen, Guowei Yang, Jia Li

llms rag safety

arXiv AI

Jul 8

CSTutorBench: Benchmarking Small Language Models as Tutors for Block-Based Programming

arXiv:2607. 05571v1 Announce Type: new Abstract: Large language models are increasingly explored as AI tutors, yet deploying them in K-12 settings raises concerns around privacy, cost, and reliance on proprietary models.

By H. Chad Lane, Bryson Kageler

llms robotics benchmarks safety

arXiv AI

Jul 8

Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction

arXiv:2607. 05568v1 Announce Type: cross Abstract: Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding.

By Gregor Kobsik, Tim Elsner, Leif Kobbelt

llms computer-vision robotics fine-tuning multimodal

arXiv AI

Jul 8

PCBWorld: A Benchmark Environment for Engine-Grounded PCB Design Automation

arXiv:2607. 05915v1 Announce Type: new Abstract: PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule-based routers.

By Hyungseok Song, Junseok Park, Won-Seok Choi, Seohui Bae, Han-Seul Jeong, Youngjoon Park, Soonyoung Lee

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 8

From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution

arXiv:2607. 06269v1 Announce Type: new Abstract: Current large language models (LLMs) are fundamentally stateless: their behavior is fully determined by input at inference time, and any higher-order cognitive architecture must be simulated at the application layer through prompt engineering and context management.

By Heting Mao

llms safety

Get the daily briefing