Large language models

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

26,493 stories · RSS feed

arXiv Machine Learning

Jun 25

Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models

arXiv:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.

By Cosimo Galeone, Anna Ettorre, Minsu Park, Giuseppe Ettorre, Daniele Ligorio

llms fine-tuning safety

arXiv Machine Learning

Jun 25

Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners

arXiv:2606. 24965v1 Announce Type: cross Abstract: Reasoning about relational structures remains a significant challenge for neural models, particularly when they must systematically apply learned knowledge to problem instances that are harder than those seen in training.

By Anirban Das, Joanne Boisson, Irtaza Khalid, Sumita Garai, Steven Schockaert

llms agents benchmarks

arXiv Machine Learning

Jun 25

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

arXiv:2606. 26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale.

By Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh, Tanwi Mallick, Sharon Li

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 25

Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets

arXiv:2606. 25760v1 Announce Type: new Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions.

By Divake Kumar, Sina Tayebati, Devashri Naik, Amanda Sofie Rios, Nilesh Ahuja, Omesh Tickoo, Ranganath Krishnan, Amit Ranjan Trivedi

llms agents multimodal benchmarks safety

arXiv Machine Learning

Jun 25

REViT: Roto-reflection Equivariant Convolutional Vision Transformer

arXiv:2606. 25318v1 Announce Type: cross Abstract: In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention.

By Sheir A. Zaheer, Alexander C. Holston, Chan Y. Park

llms computer-vision

arXiv Machine Learning

Jun 25

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

arXiv:2510. 04773v2 Announce Type: replace Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention.

By Kai Qin, Jiaqi Wu, Jianxiang He, Haoyuan Sun, Yifei Zhao, Xu Wang, Bin Liang, Yongzhe Chang, Cheng Li, Tiantian Zhang, Houde Liu

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jun 25

The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order

arXiv:2606. 24993v1 Announce Type: new Abstract: Sequential learning is order-dependent: from Pile-style next-token domain adaptation to instruction-SFT and DPO, N candidate sources induce N!

By John Sweeney

llms diffusion reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 25

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

arXiv:2606. 24937v1 Announce Type: cross Abstract: The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems.

By Haggai Roitman

llms rag agents reinforcement-learning fine-tuning efficiency safety

arXiv Machine Learning

Jun 25

TopoCast: A Topological Fidelity Framework for Evaluating Transformer-Based Time Series Forecasting

arXiv:2606. 25439v1 Announce Type: new Abstract: Deep learning-based models have achieved state-of-the-art performance in Time Series Forecasting (TSF), yet their evaluation remains dominated by pointwise error metrics such as Mean Squared Error (MSE), which quantify numerical accuracy but overlook structural properties of the forecast signal, including recurrent dynamics, oscillatory behavior, and phase alignment.

By Sandeepa Weerasekara, Sandareka Wickramanayake

llms rag benchmarks safety

arXiv Machine Learning

Jun 25

The 4/$\delta$ Bound: Designing Predictable LLM-Verifier Systems for Formal Method Guarantee

arXiv:2512. 02080v3 Announce Type: replace-cross Abstract: The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual workflows.

By Pierre Dantas, Lucas Cordeiro, Youcheng Sun, Waldir Junior

llms safety

arXiv Machine Learning

Jun 25

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

arXiv:2606. 26094v1 Announce Type: new Abstract: For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention.

By Babak Rahmani, Sebastian Dziadzio, Joschka Str\"uber, Sergio Hern\'andez-Guti\'errez, Matthias Bethge

llms agents benchmarks safety

arXiv Machine Learning

Jun 25

InvestPhilBench: A Multi-Layer Dynamic Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy

arXiv:2606. 25984v1 Announce Type: cross Abstract: Large language models are increasingly deployed as investment research assistants, yet no benchmark tests whether they can accurately reconstruct and apply the specific procedural decision frameworks of expert investors.

By Mingguang Chen, Bo Qu

llms benchmarks

arXiv Machine Learning

Jun 25

A Probabilistic Framework for LLM-Based Model Discovery

arXiv:2602. 18266v2 Announce Type: replace Abstract: Automated methods for discovering mechanistic simulator models from observational data offer a promising path toward accelerating scientific progress.

By Stefan Wahl, Raphaela Schenk, Ali Farnoud, Jakob H. Macke, Daniel Gedon

llms agents

arXiv Machine Learning

Jun 25

Flexible Gravitational-Wave Parameter Estimation with Transformers

arXiv:2512. 02968v2 Announce Type: replace-cross Abstract: Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate and complexity of observations represent a growing challenge.

By Annalena Kofler, Maximilian Dax, Stephen R. Green, Jonas Wildberger, Nihar Gupte, Jakob H. Macke, Jonathan Gair, Alessandra Buonanno, Bernhard Sch\"olkopf

llms

arXiv Machine Learning

Jun 25

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

arXiv:2606. 25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors.

By Qingyun Liu, Bo Yan, Yang Liu, Yuji Roh, Ekansh Sharma, Likang Yin, Emma Olowo, Min-hsuan Tsai, Yuxuan Li, Diego Uribe, Saksham Aggarwal, Siqi Wu, Yuan Hao, Vikas Kedigehalli, Lukasz Heldt, Lichan Hong, Li Wei, Xinyang Yi

llms rag nlp

arXiv Machine Learning

Jun 25

Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding

arXiv:2606. 24957v1 Announce Type: cross Abstract: While speculative decoding improves inference throughput for multi-batch long-context Large Language Models (LLMs), its efficiency is often limited by a verification bottleneck where Key-Value (KV) cache loading dominates latency.

By WenHung Lee, Jian-Jia Chen, Xiaolin Lin, Pei-Shuo Wang, Chi-Chih Chang, Chun-Che Yang, Ning-Chi Huang, Grace Li Zhang, Kai-Chiang Wu

llms efficiency

arXiv Machine Learning

Jun 25

Paid Voices vs. Public Feeds: Interpretable Cross-Platform Theme-Based Analysis of Climate Discourse

arXiv:2601. 13317v2 Announce Type: replace-cross Abstract: Climate discourse online shapes public understanding of climate change and informs political and policy debate, yet it unfolds across structurally different environments: paid advertising platforms host targeted, institutionally produced messaging, while public social media reflects largely organic, user-driven discussion.

By Samantha Sudhoff, Pranav Perumal, Zhaoqing Wu, Tunazzina Islam

llms

arXiv Machine Learning

Jun 25

Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents

arXiv:2605. 08442v3 Announce Type: replace-cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models.

By Jun Wen Leong

llms rag agents multimodal

arXiv Machine Learning

Jun 25

BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning

arXiv:2511. 11421v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge.

By Lan Li, Tao Hu, Da-Wei Zhou, Jia-Qi Yang, Han-Jia Ye, De-Chuan Zhan

llms multimodal benchmarks

arXiv Machine Learning

Jun 25

MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios

arXiv:2606. 24950v1 Announce Type: new Abstract: Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text.

By Patara Trirat, Jin Myung Kwak, Jay Heo, Heejun Lee, Sung Ju Hwang

llms fine-tuning benchmarks

Get the daily briefing