Large language models

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

24,787 stories · RSS feed

arXiv AI

Jul 8

Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders

arXiv:2607. 06445v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities.

By Yoav Baron, Sara Dorfman, Roni Paiss, Daniel Cohen-Or, Or Patashnik

llms diffusion multimodal

arXiv AI

Jul 8

Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion

arXiv:2607. 06546v1 Announce Type: cross Abstract: Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models.

By Shervin Khalafi, Igor Krawczuk, Sergio Rozada, Charilaos Kanatsoulis, Antonio G Marques, Alejandro Ribeiro

llms diffusion

arXiv AI

Jul 8

Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG

arXiv:2607. 05438v1 Announce Type: cross Abstract: Multimodal retrieval-augmented generation (RAG) grounds a generator in evidence drawn from heterogeneous modalities -- text, tables, and images.

By Xue Li, Yiming Gai

llms rag multimodal

arXiv AI

Jul 8

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b

arXiv:2607. 06452v1 Announce Type: cross Abstract: Biomedical question answering requires not only accurate extraction of information from scientific literature but also reliable integration of evidence across multiple documents.

By Taeyun Roh, Eunha Lee, Wonjune Jang, Sohyun Chung, Junha Jung, Jaewoo Kang

llms agents nlp

arXiv AI

Jul 8

Transformers converge to invariant algorithmic cores

arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.

By Joshua S. Schiffman

llms

arXiv AI

Jul 8

Prompt Coach: An Empirical Evaluation of an Agentic Tutor for Learning Prompt Engineering in Software Development

arXiv:2607. 06074v1 Announce Type: cross Abstract: Prompt engineering has emerged as a critical yet undertaught skill for software developers, one that traditional learning approaches are ill-equipped to support given its evolving, interactive, and context-dependent nature.

By Rohit Mehra, Kapil Singi, Vikrant Kaulgud, Vibhu Saujanya Sharma, Swapnajeet Gon Choudhury, Swati Sharma, Adam P. Burden, Majd Sakr

llms agents

arXiv AI

Jul 8

Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

arXiv:2607. 06223v1 Announce Type: new Abstract: Reinforcement learning has become a promising paradigm for improving large language model (LLM) agents on long-horizon search tasks, where the agent must make a sequence of intermediate decisions before receiving a final outcome.

By Yijun Zhang, Fan Xu, Jiaxin Ding, Yule Xie, Shiqing Gao, Xin Ding, Haoxiang Zhang, Luoyi Fu, Xinbing Wang

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 8

What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests

arXiv:2607. 05666v1 Announce Type: cross Abstract: AI coding agents are black boxes: we cannot inspect how they generate code, but we can inspect what they change.

By Illia Dovhoshliubnyi, Nima Soroush, Ashkan Sami, Alexander Brownlee

llms agents

arXiv AI

Jul 8

Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?

arXiv:2508. 01109v3 Announce Type: replace Abstract: We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational imprints in both satellite imagery (capturing features like buildings and roads) and Internet-sourced text (reflecting historical, cultural, and narratives of neighborhoods).

By Satiyabooshan Murugaboopathy, Connor T. Jerzak, Adel Daoud

llms rag agents multimodal safety

arXiv AI

Jul 8

Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation

arXiv:2607. 06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning.

By Anna C\'ordoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jes\'us Olivera

llms diffusion fine-tuning efficiency benchmarks safety

arXiv AI

Jul 8

AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models

arXiv:2607. 06485v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined.

By Cong Su, Jiaju Han, Xuemeng Sun, Chengyin Hu, Qike Zhang, Jiujiang Guo, Yiwei Wei, Jiahuan Long

llms multimodal benchmarks safety data-engineering

arXiv AI

Jul 8

Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities

arXiv:2607. 06482v1 Announce Type: cross Abstract: Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings.

By So Hasegawa, Shailaja Keyur Sampat, Lei Liu, Wei-Peng Chen

llms agents benchmarks

arXiv AI

Jul 8

Base Models Know How to Reason, Thinking Models Learn When

arXiv:2510. 07364v4 Announce Type: replace Abstract: What do thinking language models learn during training that their base models lack?

By Constantin Venhoff, Iv\'an Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Jul 8

Think Before You Grid-Search: Floor-First Triage for LLM Serving

arXiv:2607. 05876v1 Announce Type: cross Abstract: LLM serving optimization typically benchmarks many configurations and reaches for heavy profilers when latency targets are missed.

By Yihua Liu

llms agents benchmarks

arXiv Machine Learning

Jul 8

Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations

arXiv:2607. 05863v1 Announce Type: new Abstract: Negotiation is a fundamental strategic interaction in management science, characterized by agents attempting to reach agreements while protecting private information, such as reservation costs and hidden valuations.

By Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao, Xin Chen, David Simchi-Levi

llms agents reinforcement-learning

arXiv Machine Learning

Jul 8

PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint

arXiv:2607. 01646v2 Announce Type: replace Abstract: State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures across the software and hardware stack.

By Haotian Xie, Junlin Chen, Mingkai Zheng, Lishan Yang, Zhao Zhang

llms benchmarks

arXiv Machine Learning

Jul 8

How Can Mamba Learn In Context with Outliers and Generalize Provably?

arXiv:2510. 00399v2 Announce Type: replace Abstract: The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks.

By Hongkang Li, Songtao Lu, Xiaodong Cui, Pin-Yu Chen, Meng Wang

llms fine-tuning

arXiv Machine Learning

Jul 8

A Constrained Optimization Perspective of Unrolled Transformers

arXiv:2601. 17257v2 Announce Type: replace Abstract: We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms.

By Javier Porras-Valenzuela, Samar Hadou, Alejandro Ribeiro

llms nlp

arXiv Machine Learning

Jul 8

Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding

arXiv:2607. 05936v1 Announce Type: cross Abstract: Integration of web APIs is a cornerstone of modern software systems, yet writing correct web API invocation code remains challenging due to complex and evolving API specifications.

By Daniel Maninger, Leon Chemnitz, Jannis Brugger, Tushar Lamba, Amir Molzam Sharifloo, Mira Mezini

llms rag safety

arXiv AI

Jul 8

Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure Benchmarks

arXiv:2607. 05545v1 Announce Type: cross Abstract: LLM conformity is often used to describe cases where a model changes a correct answer toward a peer or group response.

By Yibo Hu, Jiaming Qu

llms benchmarks

Get the daily briefing