Large language models

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

28,285 stories · RSS feed

arXiv AI

Jun 16

Beyond Self-Attention: Sub-Quadratic Vision Transformers for Fast Image Captioning

arXiv:2606. 14753v1 Announce Type: cross Abstract: Image captioning is a challenging and significant task that aims to generate coherent and semantically meaningful textual descriptions for given images.

By Chiradeep Ghosh, Dakshina Ranjan Kisku

llms computer-vision

arXiv AI

Jun 16

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation

arXiv:2601. 05746v2 Announce Type: replace Abstract: Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving.

By Zhenghao Li, Zhi Zheng, Wei Chen, Jielun Zhao, Yong Chen, Tong Xu, Enhong Chen

llms agents benchmarks

arXiv AI

Jun 16

Beyond Case Law: Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA

arXiv:2604. 06173v2 Announce Type: replace-cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning.

By Kyubyung Chae, Jewon Yeom, Jeongjae Park, Seunghyun Bae, Ijun Jang, Hyunbin Jin, Jinkwan Jang, Taesup Kim

llms benchmarks safety

arXiv AI

Jun 16

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

arXiv:2603. 24058v2 Announce Type: replace-cross Abstract: Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analysis.

By Han Sun, Qin Li, Peixin Wang, Min Zhang

llms agents robotics multimodal benchmarks safety

arXiv AI

Jun 16

Parallel Test-Time Scaling with Multi-Sequence Verifiers

arXiv:2603. 03417v2 Announce Type: replace-cross Abstract: Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance.

By Yegon Kim, Seungyoo Lee, Chaeyun Jang, Hyungi Lee, Juho Lee

llms efficiency benchmarks

arXiv AI

Jun 16

Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning

arXiv:2603. 01696v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions.

By Haonan Jia, Shichao Dong, Xin Dong, Zenghui Sun, Jin Wang, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 16

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

arXiv:2606. 15866v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models.

By Qinjian Zhao, Zhihao Dou, Dinggen Zhang, Xiangyu Li, Chaoda Song, Zhongwei Wan, Xinpeng Li, Yanyan Zhang, Kaijie Chen, Qingtao Pan, Chengcheng Feng, Zhiqiang Gao, Xiaoyu Xia

llms agents reinforcement-learning

arXiv AI

Jun 16

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks

arXiv:2602. 09222v2 Announce Type: replace-cross Abstract: Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf.

By Georgios Syros, Evan Rose, Brian Grinstead, Christoph Kerschbaumer, William Robertson, Cristina Nita-Rotaru, Alina Oprea

llms agents safety

arXiv AI

Jun 16

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

arXiv:2605. 29796v3 Announce Type: replace Abstract: Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search.

By Yunbo Tang, Chengyi Yang, Shiyu Liu, Zhishang Xiang, Zerui Chen, Qinggang Zhang, Jinsong Su

llms agents reinforcement-learning efficiency

arXiv AI

Jun 16

Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines

arXiv:2606. 15474v1 Announce Type: new Abstract: Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down.

By Yitao Li

llms nlp

arXiv AI

Jun 16

Virtual Speech Therapist: A Clinician-in-the-Loop AI Speech Therapy Agent for Personalized and Supervised Therapy

arXiv:2605. 01101v2 Announce Type: replace Abstract: This paper develops Virtual Speech Therapist (VST), an intelligent agent-based platform that streamlines stuttering assessment and delivers customized therapy planning through automated and adaptive AI-driven workflows.

By Shakeel Sheikh, Patrick Marmaroli, MD Sahidullah, Slim Ouni, Fabrice Hirsch, Goncalo Leal, Bjorn W Schuller

llms agents benchmarks safety

arXiv AI

Jun 16

The Missing Knowledge Layer in Cognitive Architectures for AI Agents

arXiv:2604. 11364v2 Announce Type: replace Abstract: The two most influential cognitive architecture frameworks for AI agents, CoALA [21] and JEPA [12], both lack an explicit Knowledge layer with its own persistence semantics.

By Micha\"el Roynard

llms rag agents benchmarks

arXiv AI

Jun 16

Towards Verifiable Agentic Data Science: Solving Irregular TSQA Via Tool-Grounded Reasoning

arXiv:2606. 15107v1 Announce Type: new Abstract: Time series data in real-world deployments is overwhelmingly irregular.

By Sanhorn Chen, Xiaoyang Chen, Boyu Liu, Roy Zhao

llms agents nlp benchmarks

arXiv AI

Jun 16

JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory

arXiv:2509. 22888v2 Announce Type: replace Abstract: Standard LLM evaluation practices compress diverse abilities into single scores, obscuring their inherently multidimensional nature.

By Louie Hong Yao, Nicholas Jarvis, Tiffany Zhan, Saptarshi Ghosh, Linfeng Liu, Tianyu Jiang

llms rag safety

arXiv AI

Jun 16

Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning

arXiv:2510. 01444v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has advanced reasoning capabilities in multimodal large language models.

By Rui Liu, Dian Yu, Tong Zheng, Runpeng Dai, Zongxia Li, Wenhao Yu, Zhenwen Liang, Linfeng Song, Haitao Mi, Pratap Tokekar, Dong Yu

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jun 16

Computational Safety for Generative AI: A Hypothesis Testing Perspective

arXiv:2502. 12445v2 Announce Type: replace Abstract: AI safety is a rapidly growing area of research that seeks to prevent the harm and misuse of frontier AI technology, particularly with respect to generative AI (GenAI) tools that are capable of creating realistic and high-quality content through text prompts.

By Pin-Yu Chen

llms diffusion safety

arXiv AI

Jun 16

Imperfect Visual Verification for Code Edition : A Case Study on TikZ

arXiv:2606. 15693v1 Announce Type: cross Abstract: LLMs have significantly advanced code generation, enabling the synthesis of functional programs.

By Charly Reux (UR, INSA Rennes, DiverSe), Mathieu Acher (CNRS, IUF, IRISA, UR, DiverSe), Djamel Eddine Khelladi (DiverSe, UR, CNRS, IRISA), Cl\'ement Quinton (SPIRALS, CNRS), Olivier Barais (UR, IRISA, DiverSe)

llms benchmarks

arXiv AI

Jun 16

MAF: Multimodal Adaptive Few-shot Prompting for Sentiment Analysis with MLLMs

arXiv:2606. 15694v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in understanding complex multimodal content.

By Hangling Xie

llms nlp multimodal benchmarks

arXiv AI

Jun 16

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

arXiv:2606. 15441v1 Announce Type: cross Abstract: Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution.

By Lipeng He, Yihan Wang, Jiawen Zhang, N. Asokan

llms rag agents reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 16

Medical Heuristic Learning: An LLM-Driven Framework for Interpretable and Auditable Clinical Decision Rules

arXiv:2606. 16337v1 Announce Type: new Abstract: Predictive modeling for clinical tabular data is central to clinical decision support and therefore requires not only strong predictive performance but also transparent decision logic.

By Wei Xu, Ke Yang, Gang Luo, Keli Zheng, Lingyan Hu, Jing Wang, Kefeng Li

llms benchmarks

Get the daily briefing