Large language models

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

31,695 stories · RSS feed

arXiv Machine Learning

Jun 2

A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL

arXiv:2606. 02398v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation, question answering, and creative writing (CW), but training on one domain often degrades performance on others.

By Lei Yang, Siyu Ding, Deyi Xiong

llms nlp reinforcement-learning

arXiv AI

Jun 2

Joint Agent Memory and Exploration Learning via Novelty Signals

arXiv:2606. 01528v1 Announce Type: new Abstract: In open-ended environments, exploration is fundamental for autonomous agents, yet current language model agents struggle with this.

By Shizuo Tian, Xiaohong Weng, Rui Kong, Yuxuan Chen, Guohong Liu, Yuebing Song, Jiacheng Liu, Yuchen Li, Dawei Yin, Ting Cao, Yunxin Liu, Yuanchun Li

llms agents

arXiv Machine Learning

Jun 2

Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving

arXiv:2606. 01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives.

By Jianru Ding, Ryien Hosseini, Pouya Mahdi Gholami, Mingyuan Xiang, Henry Hoffmann

llms agents efficiency

arXiv Machine Learning

Jun 2

Human in the Loop Adaptive Optimization for Improved Time Series Forecasting

arXiv:2505. 15354v2 Announce Type: replace Abstract: Time series forecasting models often produce systematic, predictable errors even in critical domains such as energy, finance, and healthcare.

By Malik Tiomoko, Hamza Cherkaoui, Giuseppe Paolo, Zhang Yili, Yu Meng, Zhang Keli, Hafiz Tiomoko Ali

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 2

Can Vision Language Models Learn Intuitive Physics from Interaction?

arXiv:2602. 06033v2 Announce Type: replace Abstract: Pre-trained vision language models do not have good intuitions about the physical world.

By Luca M. Schulze Buschoff, Konstantinos Voudouris, Can Demircan, Eric Schulz

llms reinforcement-learning fine-tuning

arXiv AI

Jun 2

PropLLM: Propagation-Aware Scene Reconstruction for Network Fault Diagnosis

arXiv:2606. 00582v1 Announce Type: new Abstract: Network faults propagate layer by layer along topology and protocol dependencies, yet operations systems typically observe only symptomatic alerts at the tail end of propagation chains, where distinct root-cause faults may produce highly similar end-point symptoms.

By Zongzong Wu, Ming Zhao, Fengxiao Tang, Nei Kato

llms multimodal safety

arXiv Machine Learning

Jun 2

Reconsidering Positional Supervision in Masked Diffusion Language Model Training

arXiv:2601. 22947v2 Announce Type: replace-cross Abstract: Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive language models.

By Mengyu Ye, Keito Kudo, Ryosuke Takahashi, Jun Suzuki

llms diffusion fine-tuning benchmarks safety

arXiv AI

Jun 2

Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs

arXiv:2606. 00050v1 Announce Type: new Abstract: We present Grokers, an architecture for building persistent, structured comprehension of typed knowledge graphs through bottom-up inductive traversal of dependency subgraphs.

By Gregory Magarshak

llms rag agents

arXiv AI

Jun 2

Agent Guide: A Simple Agent Behavioral Watermarking Framework

arXiv:2504. 05871v3 Announce Type: replace Abstract: The increasing deployment of intelligent agents in digital ecosystems, such as social media platforms, has raised significant concerns about traceability and accountability, particularly in cybersecurity and digital content protection.

By Kaibo Huang, Zipei Zhang, Zhongliang Yang, Linna Zhou

llms agents nlp

arXiv AI

Jun 2

From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures

arXiv:2602. 04861v2 Announce Type: replace-cross Abstract: Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading to erroneous behavior in downstream simulations that standard energy and force regression evaluations can miss.

By Ryan Liu, Eric Qu, Tobias Kreiman, Samuel M. Blau, Aditi S. Krishnapriyan

llms benchmarks

arXiv AI

Jun 2

PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning

arXiv:2606. 02443v1 Announce Type: cross Abstract: Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible.

By Yusong Zhao, Yuejin Xie, Youliang Yuan, Junjie Hu, Jitian Guo, Yujiu Yang, Pinjia He

llms multimodal benchmarks safety

arXiv AI

Jun 2

Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning

arXiv:2603. 24324v4 Announce Type: replace-cross Abstract: Designing effective auxiliary rewards for cooperative multi-agent systems remains challenging, as misaligned incentives can induce suboptimal coordination, particularly when sparse task rewards provide insufficient grounding for coordinated behavior.

By Dogan Urgun, Gokhan Gungor

llms agents reinforcement-learning safety

arXiv AI

Jun 2

Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture

arXiv:2606. 00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology.

By Hai Lin

llms agents safety

arXiv Machine Learning

Jun 2

Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs

arXiv:2602. 11641v2 Announce Type: replace Abstract: Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information.

By Yinlin Zhu, Di Wu, Xu Wang, Guocong Quan, Miao Hu

llms rag benchmarks safety

arXiv AI

Jun 2

Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments

arXiv:2602. 23234v4 Announce Type: replace-cross Abstract: Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for.

By Evangelia Christakopoulou, Vivekkumar Patel, Hemanth Velaga, Sandip Gaikwad, Sean Suchter, Venkat Sundaranatha

llms fine-tuning

arXiv AI

Jun 2

Construction of Historical Knowledge Graphs Based on BERT and Graph Neural Networks

arXiv:2606. 01747v1 Announce Type: cross Abstract: Through digital humanities research and scale-up historical data analysis, a significant amount of traditional historical text is converted into structured knowledge graphs.

By Ping Li, Bartlomiej Brzozka

llms multimodal

arXiv Machine Learning

Jun 2

WildCat: Near-Linear Attention in Theory and Practice

arXiv:2602. 10056v2 Announce Type: replace Abstract: We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks.

By Tobias Schr\"oder, Lester Mackey

llms diffusion computer-vision efficiency benchmarks

arXiv Machine Learning

Jun 2

The Attribution Contract: Feature Attribution for Generative Language Models

arXiv:2605. 23080v2 Announce Type: replace Abstract: Feature attribution methods promise to identify which input features matter for a model output.

By Giang Nguyen

llms diffusion

arXiv AI

Jun 2

Shortcut to Nowhere: Demystifying Deep Spurious Regression

arXiv:2606. 01723v1 Announce Type: cross Abstract: Real-world regression often exhibits shortcuts: attributes that are spuriously correlated with continuous targets in training, yet unreliable under deployment shifts; regressing targets using such shortcuts may fail catastrophically at test time.

By Guanrong Xu, Jessica Li, Hao Wang, Yuzhe Yang

llms computer-vision benchmarks

arXiv Machine Learning

Jun 2

MINES: Explainable Anomaly Detection through Web API Invariant Inference

arXiv:2512. 06906v2 Announce Type: replace-cross Abstract: Detecting the anomalies of web applications, important infrastructures for running modern companies and governments, is crucial for providing reliable web services.

By Wenjie Zhang, Yun Lin, Chun Fung Amos Kwok, Xiwen Teoh, Xiaofei Xie, Frank Liauw, Hongyu Zhang, Jin Song Dong

llms benchmarks

Get the daily briefing