Large language models

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

23,195 stories · RSS feed

arXiv AI

Jul 10

Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback

arXiv:2602. 12612v2 Announce Type: replace-cross Abstract: Traditional methods for automating recommender system design, such as Neural Architecture Search (NAS), are often constrained by a fixed search space defined by human priors, limiting innovation to pre-defined operators.

By Sein Kim, Sangwu Park, Hongseok Kang, Wonjoong Kim, Jimin Seo, Yeonjun In, Kanghoon Yoon, Hyunsik Jeon, Chanyoung Park

llms benchmarks

arXiv AI

Jul 10

SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets

arXiv:2607. 08681v1 Announce Type: new Abstract: As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness.

By Shilin Ou, Yifan Xu, Luyao Zhang

llms agents reinforcement-learning benchmarks safety

arXiv AI

Jul 10

TAG: A Lightweight Framework for Test-Driven Agentic Artifact Generation

arXiv:2607. 02615v2 Announce Type: replace-cross Abstract: Generating structured artifacts with Large Language Models - e.

By Yaniv Melamed, Yoni Zukerman, Michal Shechter, Miri Weissler, Ashwin Patil, Hani Neuvirth-Telem

llms agents safety

arXiv AI

Jul 10

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

arXiv:2606. 25984v2 Announce Type: replace 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

Jul 10

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

arXiv:2601. 22448v2 Announce Type: replace Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when.

By Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui, Rongzhi Zhang, Changlong Yu, Shuowei Jin, Jingfeng Yang, Qingyu Yin, Zhengyang Wang, Zheng Li, Yifan Gao, Priyanka Nigam, Bing Yin, Lihong Li, Yangqiu Song

llms reinforcement-learning benchmarks

arXiv AI

Jul 10

WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search

arXiv:2607. 08662v1 Announce Type: cross Abstract: Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-oriented tasks.

By Xiaoshuai Song, Liancheng Zhang, Kangzhi Zhao, Yutao Zhu, Zhongyuan Wang, Guanting Dong, Jinghan Yang, Han Li, Kun Gai, Ji-Rong Wen, Zhicheng Dou

llms agents nlp benchmarks

arXiv Machine Learning

Jul 10

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment

arXiv:2607. 08029v1 Announce Type: new Abstract: The emergence of vision language models with fewer than 3 billion parameters has accelerated the implementation of on-device multimodal intelligence.

By Hyeju Shin, Chorwon Kim, Ryangsoo Kim, Hark Yoo, Jaein Kim

llms efficiency multimodal safety

arXiv AI

Jul 10

Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO

arXiv:2602. 17686v4 Announce Type: replace-cross Abstract: Distilling Chain-of-Thought (CoT) reasoning from large language models into compact student models presents a fundamental challenge: teacher rationales are often too verbose for smaller models to faithfully reproduce.

By Bowen Yu, Maolin Wang, Sheng Zhang, Binhao Wang, Yi Wen, Jingtong Gao, Bowen Liu, Zimo Zhao, Wanyu Wang, Xiangyu Zhao

llms efficiency safety

arXiv AI

Jul 10

Validity of LLMs as data annotators: AMALIA on authority

arXiv:2607. 08731v1 Announce Type: cross Abstract: A national language model offers a linguistic community its own instrument for measuring what its citizens say and value.

By Manuel Pita

llms benchmarks

arXiv AI

Jul 10

VEGAS: Human-Aligned Video Caption Evaluation via Gaze

arXiv:2607. 08489v1 Announce Type: cross Abstract: Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention.

By Shenghui Chen, Po-han Li, Ximeng Sun, Shijia Yang, Emad Barsoum, Zicheng Liu, Sandeep Chinchali, Ufuk Topcu

llms multimodal

arXiv AI

Jul 10

A Practical Investigation of Training-free Relaxed Speculative Decoding

arXiv:2607. 08690v1 Announce Type: cross Abstract: Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM.

By Guoxuan Xia, Luka Ribar, Paul Balanca

llms benchmarks

arXiv AI

Jul 10

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

arXiv:2601. 22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design.

By Zhuochun Li, Yong Zhang, Ming Li, Yuelyu Ji, Yiming Zeng, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao, Daqing He

llms benchmarks

arXiv Machine Learning

Jul 10

Uncertainty-gated selection for block-sparse attention

arXiv:2607. 07724v1 Announce Type: new Abstract: Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks.

By Thomas Rossi

llms

arXiv AI

Jul 10

From Legacy Documentation to OSCAL: An MCP-Based Agent Pipeline for Threat-Informed Continuous Compliance in Critical Infrastructure

arXiv:2607. 08288v1 Announce Type: cross Abstract: In critical infrastructure, operational technology environments often cannot be actively scanned, and yet active system feedback is needed for risk assessment and compliance.

By Lea Roxanne Muth, Marian Margraf

llms agents safety

arXiv AI

Jul 10

Applying JEPA-Style Predictive Learning to JA4-Derived Network Fingerprints

arXiv:2607. 08465v1 Announce Type: new Abstract: I-JEPA and V-JEPA learn by matching latent predictions to target encoder outputs rather than regenerating the original input, and this has worked well for images and video.

By Javier Izquierdo, Aygul Zagidullina

llms rag

arXiv AI

Jul 10

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

arXiv:2607. 07907v1 Announce Type: cross Abstract: With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associations that originate from their training data.

By Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, Vaidehi Patil

llms multimodal benchmarks

arXiv AI

Jul 10

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

arXiv:2607. 07903v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit remarkable capabilities but remain highly vulnerable to adversarial prompts and jailbreak attacks.

By Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang, Longwei Wang

llms benchmarks safety

arXiv AI

Jul 10

Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems

arXiv:2607. 07989v1 Announce Type: cross Abstract: Large language model (LLM) based multi-agent systems enable complex problem solving through coordinated reasoning and action, but their distributed structure also introduces new challenges in diagnosing system-level failures.

By Yufei Xia, Anjun Gao, Yueyang Quan, Zhuqing Liu, Minghong Fang

llms agents fine-tuning benchmarks

arXiv AI

Jul 10

WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving

arXiv:2607. 08375v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving.

By Xuerun Yan, Zhexi Lian, Nuoheng Zhang, Shiyu Fang, Haoran Wang, Chen Lv, Jia Hu, Binyang Song

llms agents diffusion robotics multimodal benchmarks safety

arXiv AI

Jul 10

Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation

arXiv:2607. 08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students.

By Miseong Shawn Kim

llms reinforcement-learning fine-tuning efficiency safety

Get the daily briefing