Large language models

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

30,670 stories · RSS feed

arXiv Computer Vision

Sep 30

VoxelSage: Tool-Augmented 3D CT Analysis and Simulator-Shielded Sequential Resection Planning for Liver Tumors

arXiv:2609.37648v1 Announce Type: new Abstract: Preoperative liver-tumor assessment requires segmentation, physical-space measurement, visual evidence, and resection planning from the same three-dime...

By Binghong Qian, Xuanhe Liu, Yifan Xing, Wenjie Deng, Jian Wu, Haochao Ying

llms agents computer-vision multimodal safety

arXiv AI

Sep 30

GeoOutageBench: Benchmarking Ambiguity-aware, Ontology-grounded Geospatiotemporal KGQA for Multimodal Power Outage and Resilience Analysis

arXiv:2609.36082v1 Announce Type: new Abstract: We introduce GeoOutageBench, a benchmark for assessing LLM-based geospatiotemporal KGQA for multimodal outage and resilience analysis. Unlike existing...

By Ethan D. Frakes, Amy Kvien, Rishabh Kundu, Redad Mehdi, Van D. Tran, Vibha S. Mandayam, Kristopher O. Davis, Erika I. Barcelos, Roger H. French, Yinghui Wu, Mengjie Li

llms multimodal benchmarks

arXiv AI

Sep 30

Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models

arXiv:2609.36254v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) are commonly trained with reinforcement learning (RL) to improve their generation of chain-of-thought (CoT) reasoning bef...

By Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan, Alexander Kotov, Dongxiao Zhu

llms reinforcement-learning benchmarks safety

arXiv AI

Sep 30

Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruning

arXiv:2609.36359v1 Announce Type: new Abstract: Graph-based approximate nearest neighbor search (ANNS) is widely used for large-scale semantic search. Its indices are constructed primarily based on g...

By Fangzhou Wu, Haike Xu, Sandeep Silwal

llms rag efficiency benchmarks

arXiv AI

Sep 30

ARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering

arXiv:2609.36392v1 Announce Type: new Abstract: In diseases where clinical guidelines are incomplete, contested, or mutually contradictory, knowledge completeness and dynamic conflict-aware synthesis...

By Yuyan Chen

llms rag agents nlp benchmarks safety

arXiv AI

Sep 30

Support-Set Target Leakage in Relational Foundation Models during In-Context Learning: Model Dependence and Evaluation Reliability

arXiv:2609.36417v1 Announce Type: new Abstract: Relational in-context learning (ICL) uses labeled support examples and their linked relational context to predict labels for new queries. This creates...

By Roshan Reddy Upendra, Alexandre Dorais, Joe Meyer, Andrew Pouret, Anastasios Lambrianos Stappas, Dinesh Katupputhur Ramprasath, Viswanath Ganapathy, Tom Palczewski, Minghua Li

llms

arXiv AI

Sep 30

Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models

arXiv:2609.36828v1 Announce Type: new Abstract: Post-training quantization (PTQ) lowers deployment cost for multimodal large language models, but calibration typically reconstructs fixed sequences wi...

By Wenxiao Fan, Jingling Fu, Lichen Ma, Yu He, Luohang Liu, Jinbao Xue, Ke Zhang, Junshi Huang, Kan Li

llms efficiency multimodal

arXiv AI

Sep 30

ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction

arXiv:2609.36835v1 Announce Type: new Abstract: Long-context large language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for...

By Zheyu Shen, Guanhua Wang, Dezhan Tu, Mengchi Zhang, Yanjia Li, Adnan Aziz, Chunqiang Tang, Ang Li

llms efficiency safety

arXiv AI

Sep 30

actr: aligning thoughts and responses for multilingual safety in reasoning llms

arXiv:2609.37054v1 Announce Type: new Abstract: Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to jai...

By Xianhui Zhang, Jian Yu, Chengyu Xie, Chenhang Cui, Shuyi Miao, Pengyang Shao, Yu Zheng, Fei Shen, Tat-Seng Chua

llms benchmarks safety

arXiv AI

Sep 30

Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing

arXiv:2609.37362v1 Announce Type: new Abstract: Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--eff...

By Guannan Lai, Han-Jia Ye

llms

arXiv AI

Sep 30

Authority Before Utility: Non-Compensatory Control for Persistent LLM Memory

arXiv:2609.37474v1 Announce Type: new Abstract: Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion,...

By Wesley Shu

llms

arXiv AI

Sep 30

Rational Clarification by Assistive Agents via Value-of-Information Reasoning

arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the...

By T. Duy Nguyen-Hien, Yee Whye Teh, Wee Sun Lee, Tan Zhi-Xuan

llms agents nlp fine-tuning

arXiv AI

Sep 30

How to Run Statistics over LLM Judges and Trust the Results: Calibrated Inference for Small-Sample AI Evaluation with evalstats

arXiv:2609.35815v1 Announce Type: cross Abstract: Researchers across academia increasingly base significance claims on LLM judge scores and small-sample AI evaluations. Yet without well-calibrated co...

By Ian Arawjo

llms safety

arXiv AI

Sep 30

The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models

arXiv:2609.35860v1 Announce Type: cross Abstract: Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors a...

By Pranav Darshan, Pranav A, Sravan Karthick T, Minal Moharir, Ivan P. Yamshchikov

llms diffusion nlp safety

arXiv AI

Sep 30

SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents

arXiv:2609.35889v1 Announce Type: cross Abstract: Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing...

By Xiaoyu Xu, Zi Liang, Minxin Du, Qipeng Xie, Qingqing Ye, Yuyuan Li, Haibo Hu

llms agents benchmarks

arXiv AI

Sep 30

MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?

arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that ag...

By Lingqi Jiang, Jialuo Chen, Jianan Ma, Xinhao Deng, Xiaohu Du, Sibo Yi, Yuqi Qing, Zhenguang Liu, Qinming He, Shiwen Cui, Changhua Men

llms agents multimodal benchmarks safety

arXiv AI

Sep 30

Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models

arXiv:2609.36577v1 Announce Type: cross Abstract: Audio large language models (ALLMs) can reason about the content of audio recordings to perform complex tasks. However, these capabilities usually co...

By Zhenhong Zhou, Xuanyue Zhao, Youji Liu, Yuanhe Zhang, Xiaoyu Ma, Lianyu Hu, Yang Liu

llms

arXiv AI

Sep 30

VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction

arXiv:2609.36804v1 Announce Type: cross Abstract: Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and gramm...

By Yitong Han, Nankai Lin, Juan Luo, Hongyan Wu, Lianxi Wang, Shengyi Jiang

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Sep 30

Cross-Organizational SysML Model Integration: A Survey of Challenges and AI-Supported Tasks

arXiv:2609.37000v1 Announce Type: cross Abstract: Cross-organizational collaboration is widely regarded as a key promise of SysML-based Model-Based Systems Engineering (MBSE), yet practitioners still...

By Zirui Li, Torsten Brix, Stephan Husung

llms safety

arXiv AI

Sep 30

ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents

arXiv:2609.37196v1 Announce Type: cross Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allow...

By Yanjie Li, Xiangyu He, Xuelong Dai, Bin Xiao

llms agents multimodal

Get the daily briefing