Large language models

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

29,718 stories · RSS feed

arXiv AI

Sep 30

CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles

arXiv:2609.36218v1 Announce Type: cross Abstract: Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, and cybersecurity, yet film rema...

By Mir Tafseer Nayeem, Susmoy Chakraborty, Davood Rafiei

llms benchmarks safety

arXiv AI

Sep 30

MoRE: Scaling mixture of experts with hardware-aware low-rank routing

arXiv:2609.36301v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts. In this regim...

By Honam Wong, Surbhi Goel, Enric Boix-Adser\`a

llms benchmarks

arXiv AI

Sep 30

Quantization Enables Private Dense Retrieval against Malicious Service Providers

arXiv:2609.36376v1 Announce Type: cross Abstract: Dense retrieval, the key component of Retrieval Augmented Generation (RAG), retrieves the most relevant documents by comparing dense vector represent...

By Louis Tremblay Thibault, Sofiane Azogagh, Marc-Olivier Killijian, Ulrich A\"ivodji

llms rag efficiency safety

arXiv AI

Sep 30

LLMs Learn to Evade Latent Monitors from Prior Feedback Alone

arXiv:2609.36490v1 Announce Type: cross Abstract: Latent space monitors aim to detect undesired behaviors in LLM agents by inspecting an agent's internal activations rather than its outputs. However,...

By Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani

llms agents diffusion fine-tuning benchmarks

arXiv AI

Sep 30

How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective

arXiv:2609.36557v1 Announce Type: cross Abstract: Medical Vision-Language Models (VLMs) show significant promise for clinical image understanding, offering accurate diagnosis with interpretable reaso...

By Janet Wang, Yunbei Zhang, Xiao Wang, Jihun Hamm

llms rag fine-tuning multimodal

arXiv AI

Sep 30

FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution

arXiv:2609.36651v1 Announce Type: cross Abstract: Long-context reasoning in large language models incurs substantial computation and memory costs. Visual text compression (VTC) reduces input length b...

By FangZhi Zhong, Xuerui Qiu, Yuqi Pan, Ya Liu, Shaowei Gu, Bo Xu, Guoqi Li

llms fine-tuning multimodal

arXiv AI

Sep 30

Frontier Autolab: Organizational Memory, Adversarial Dissent and Temporal Leakage in Multi-Agent LLM Firms Across Fifty Years of Technological Change

arXiv:2609.36739v1 Announce Type: cross Abstract: Multi-agent LLM systems are increasingly structured like organizations, with roles, critics and shared memory, yet they are evaluated on tasks that l...

By Bravish Ghosh

llms agents benchmarks safety

arXiv AI

Sep 30

SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs

arXiv:2609.36879v1 Announce Type: cross Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent...

By Haoran Ou, Gelei Deng, Xuanye Zhang, Wenbo Guo, Tianwei Zhang, Kwok-Yan Lam

llms agents efficiency

arXiv AI

Sep 30

Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

arXiv:2609.36849v1 Announce Type: cross Abstract: Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns...

By Omar Sheta, Rinku Deuja, Hadi Masoudi, Minghong Fang

llms safety

arXiv AI

Sep 30

Purlin: Separating Orchestration from the Datapath of Collectives

arXiv:2609.36954v1 Announce Type: cross Abstract: Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing...

By Osayamen Jonathan Aimuyo, Swapnil Gandhi, Christos Kozyrakis

llms agents diffusion efficiency

arXiv AI

Sep 30

LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter

arXiv:2609.37029v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context...

By Hao-Yuan He, Peng-Fei Liu, Si Shen, Ming Li

llms diffusion benchmarks

arXiv AI

Sep 30

Beam Search as Test-Time Self-Distillation via Counterfactual Contexts

arXiv:2609.37041v1 Announce Type: cross Abstract: Self-Distillation Fine-Tuning (SDFT) enables a language model to act as its own teacher: by conditioning on a demonstration, the model produces an im...

By Su Ee Tan, Xiaotong Ji, Rasul Tutunov, Haitham Bou-Ammar, Matthieu Zimmer

llms fine-tuning efficiency benchmarks

arXiv AI

Sep 30

Beyond Semantic Narrowing: Robust and Efficient LLM Watermarking with Hamming Neighborhoods

arXiv:2609.37218v1 Announce Type: cross Abstract: Semantic watermarking improves robustness against watermark removal attacks by embedding detectable signals into sentence-level representations. Howe...

By Zewen Sun, Tongyang Zhao, Liyao Xiang, Mingxuan Ma, Lingzhe Wang, Zhiyuan Li

llms rag

arXiv AI

Sep 30

DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis

arXiv:2609.37233v1 Announce Type: cross Abstract: Datalog underpins reasoning tasks such as program analysis, but its programs are hard to write. Existing synthesizers automate this task but require...

By Yuan Li, Hanyun Jiang, Guowei Tian, Chengpeng Wang, Peisen Yao

llms agents benchmarks

arXiv AI

Sep 30

Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring

arXiv:2609.37312v1 Announce Type: cross Abstract: Can reasoning models trick chain of thought (CoT) monitors and perform hidden computation without revealing it in their thinking traces? We show that...

By Mohammadali Mohammadkhani, Madhava Krishna, Yash Sarrof, Michael Hahn

llms

arXiv AI

Sep 30

TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG

arXiv:2609.37349v1 Announce Type: cross Abstract: Multi-step visual retrieval-augmented generation (RAG) answers complex questions by repeatedly retrieving visual evidence, updating an intermediate s...

By Yalun Wu, Bingzhou Wang, Boyang Wang, Peiying Wang, Shaojie He, Yunhan Wang, Shaozu Yuan, Jiawei Wang

llms rag multimodal

arXiv AI

Sep 30

LazySloth: Bounded LLM-based Lazy Tree Search for Fast Long Video Comprehension

arXiv:2609.37426v1 Announce Type: cross Abstract: Modern vision-language models (VLMs) have shown promising results in long-video understanding due to the rich semantic information they can capture....

By Arka Mukherjee, Kaleen Shrestha, Larissa Zhu, Maja Matari\'c

llms rag agents multimodal benchmarks

arXiv AI

Sep 30

Regime Boundary Alignment for Evidence-Gated Question Answering

arXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence...

By Zeyan Li, Qirong Guo, SIyuan Qiu, Hu Xu, Chun Li, Jianfeng Xu

llms rag nlp fine-tuning safety

arXiv AI

Sep 30

Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning

arXiv:2609.37554v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as high-level planners in robot navigation, but their outputs may become unreliable when instructi...

By {\L}ukasz Sobczak, Nur Kele\c{s}o\u{g}lu, S{\l}awomir Piotr Nowak

llms robotics benchmarks safety

arXiv AI

Sep 30

Making Duplicate Reimbursement Unrepresentable: A Verified Ethereum E-Invoice System for Humans and AI Agents

arXiv:2609.37819v1 Announce Type: cross Abstract: Electronic invoices are replacing paper invoices worldwide, but today's centralized architectures leave three problems unsolved on the consumption si...

By Jia Cai

llms agents benchmarks safety

Get the daily briefing