Large language models

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

18,755 stories · RSS feed

arXiv AI

Jul 29

How Often Should a Recommender Call an LLM? Value-Weighted Routing, Monitoring, and Seasonal Robustness

arXiv:2607. 25068v1 Announce Type: new Abstract: Routing decisions between a cheap heuristic and an expensive large language model (LLM) are typically framed as a difficulty problem: send the hard cases to the expensive path.

By Bhavtosh Rath

llms

arXiv AI

Jul 29

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

arXiv:2607. 25091v1 Announce Type: new Abstract: The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated.

By Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray

llms agents reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jul 29

How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation

arXiv:2607. 25140v1 Announce Type: new Abstract: This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and appraise one another.

By Funda Durupinar

llms agents

arXiv AI

Jul 29

When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops

arXiv:2607. 25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention.

By Hyundoo Park, Byungho Choi

llms agents safety

arXiv AI

Jul 29

PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention

arXiv:2607. 25157v1 Announce Type: new Abstract: Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretraining with bidirectional denoising.

By Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Jesson Wang, Siheng Wang, Guang Yang, Haoyan Xu, Chenhao Wei, Zhengqing Yuan, Youran Shen, Yanfang Ye, Junhao Dong

llms diffusion fine-tuning

arXiv AI

Jul 29

ContractHIL-HLS: Contract-Aligned Multi-Agent Workflow with Hardware-in-the-Loop Feedback for HLS Design

arXiv:2607. 25283v1 Announce Type: new Abstract: This paper presents ContractHIL-HLS, a contract-aligned multi-agent workflow for practical high-level synthesis (HLS) engineering.

By Jingbo Zhang, Haoxiang Sun, Wenbo Wang, Wenbo Zhang

llms agents safety

arXiv AI

Jul 29

Context Assembly as the Controlled Variable: A Control-Theoretic View of Harness Policies for Frozen LLM Agents

arXiv:2607. 25408v1 Announce Type: new Abstract: A growing body of 2026 work applies control theory to LLM agents: Lyapunov-certified stability for tool-mediated controllers (Prinos et al.

By Debjyoti Paul

llms agents reinforcement-learning

arXiv AI

Jul 29

The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play

arXiv:2607. 25425v1 Announce Type: new Abstract: Capture the Flag (CTF) competitions are among cybersecurity's most effective training grounds, developing practical skill across cryptography, web exploitation, and binary exploitation.

By Michael Macaulay, Harmony Bouabid, Guo Gen Ang, Sasha Shaw

llms benchmarks safety

arXiv AI

Jul 29

TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation

arXiv:2607. 25471v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) and Large Language Models (LLMs) have each advanced recommendation systems by modeling structural and semantic signals, respectively.

By He Ma, Chen Liu

llms rag benchmarks

arXiv AI

Jul 29

PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents

arXiv:2607. 25485v1 Announce Type: new Abstract: Health AI is evolving from answering questions to agentic systems that converse with patients, reason about health records, and act on their behalf.

By Korosh Vatanparvar, Ashutosh Joshi, Maria Xenochristou, Mohammad Abuzar Hashemi, Prasad Kasu, Deepak Bansal, Daniel Lopez-Martinez, Anchal Nema, Ramya Ganesan, Will Kimbrough, Alex Woody, Yadunandana Rao, Dilek Hakkani-Tur, Wilko Schulz-Mahlendorf

llms agents benchmarks safety

arXiv AI

Jul 29

Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention

arXiv:2607. 25576v1 Announce Type: new Abstract: Photoacoustic tomography (PAT) combines the optical absorption contrast of biological tissue with the spatial resolution of ultrasound, yet recovering the initial pressure distribution from sparse-view sensor measurements remains an ill-posed inverse problem.

By Mary John, Shibili Said, Imad Barhumi, Sherzod Turaev, Mohamed Yahia

llms benchmarks

arXiv AI

Jul 29

Beyond Epistemia: Epistemic Schizologia and Large Language Models as Techno-Semiotic Machines

arXiv:2607. 25620v1 Announce Type: new Abstract: Quattrociocchi and colleagues warn that the fluent outputs of large language models may allow linguistic plausibility to substitute for epistemic evaluation, producing the condition they call *Epistemia*: the experience of possessing knowledge without undertaking the practices through which judgment would ordinarily be warranted.

By Federico Cabitza, Gianluca Colombo

llms agents robotics

arXiv AI

Jul 29

OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs

arXiv:2607. 25669v1 Announce Type: new Abstract: Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but their long audio-video token sequences introduce substantial memory and inference costs.

By Haoyang Huang, Wenjie Huang, Tianqi Xu, Hongyaoxing Gu, Kang Tan, Yikai Fu, Yuhao Shen, Tianyu Liu, Baolin Zhang, Jun Zhang, Xinyi Hu, Jun Dai, Shuang Ge, Lei Chen, Yue Li, Mingchen Wang, Meng Zhang

llms efficiency benchmarks

arXiv AI

Jul 29

Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL

arXiv:2607. 25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results.

By Jiabao Ji, Yujian Liu, Li An, Rohit Jain, Gungor Polatkan, Siyu Zhu, Shiyu Chang

llms agents reinforcement-learning efficiency

arXiv AI

Jul 29

DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation

arXiv:2607. 24745v1 Announce Type: cross Abstract: Key Information Extraction (KIE) is vital for many document applications, but creating training datasets is traditionally a time-consuming manual process.

By Siddartha Reddy, Harikrishnan P M, Goutham Vignesh, Varun V, Vishal Vaddina

llms computer-vision fine-tuning benchmarks

arXiv AI

Jul 29

From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance

arXiv:2607. 24791v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is the dominant paradigm for applying large language models (LLMs) to enterprise document corpora, yet naive implementations encounter hard limits as corpus scale and query complexity grow.

By Mishca de Costa, Muhammad Saleh Anwar, Dave Mercier, Issam Hammad

llms rag agents nlp fine-tuning

arXiv AI

Jul 29

Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs

arXiv:2607. 24799v1 Announce Type: cross Abstract: Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning.

By Alexandru-Andrei Sauc\u{a}, Ana-Luiza Rusnac

llms rag fine-tuning multimodal benchmarks

arXiv AI

Jul 29

REPREC: Representation Driven Parameter-Efficient Recommendation System

arXiv:2607. 24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task.

By Harshini Kavuru, Dwipam Katariya, Giri Iyengar, Pranab Mohanty, Kalanand Mishra, Kalanand Mishra

llms rag fine-tuning efficiency benchmarks safety

arXiv AI

Jul 29

Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed

arXiv:2607. 24898v1 Announce Type: cross Abstract: State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users.

By Xinnuo Xu, Anja Thieme, Daniela Massiceti, Ioana Tanase, Rita Marques, Melanie Fernandez Pradier, Martin Grayson, Camilla Longden, Cecily Morrison

llms diffusion fine-tuning multimodal benchmarks safety

arXiv AI

Jul 29

Stable FP4 Training via Transposition-Invariant Block Quantization

arXiv:2607. 24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization.

By Mehdi Rahimifar, Amin Darabi, Mehran Taghian Jazi, Xing Huang, Yao Wang, Zhijun Tu, Yufei Cui, Yunke Peng, Hongliang Li

llms efficiency

Get the daily briefing