Large language models

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

32,584 stories · RSS feed

arXiv AI

Sep 10

STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models

arXiv:2609.05916v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose subs...

By Yichen Guo, Tinghao Wang, Qizhe Zhang, Lingbei Meng, Yuan Zhang, Jiajun Cao, Hao Jiang, Chenwei Wu, Jixian Wu, Sixiang Chen, Tao Luo, Hongyang Cheng, Kai Tang, Chenxi Li, Renyuan Li, Xiande Huang, Wenya Wang, Shanghang Zhang

llms efficiency multimodal benchmarks

arXiv AI

Sep 10

When and Why LLM Causal Priors Help: Closed-Loop Prior Selection for Amortized Causal Inference

arXiv:2609.06941v1 Announce Type: new Abstract: Causal effect estimation asks how an outcome would change under an intervention, and medicine, economics, and public policy all treat it as a foundatio...

By Haohao Zhou

llms

arXiv AI

Sep 10

VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha Discovery

arXiv:2609.07065v1 Announce Type: new Abstract: Agent-to-agent (A2A) alpha discovery is slowed by repeated feedback cycles between mining and evaluation agents, whose hand-offs, in contemporary LLM m...

By Yuqi Li, Siyuan Liu, Bingjun Liu

llms agents benchmarks

arXiv AI

Sep 10

Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems

arXiv:2609.05928v1 Announce Type: cross Abstract: Large language models now compute correct tax liabilities on over 90% of well-formed cases in statutory benchmarks, which makes them candidates for t...

By Albert Sadowski, Jaros{\l}aw A. Chudziak

llms benchmarks

arXiv AI

Sep 10

Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets

arXiv:2609.07095v1 Announce Type: new Abstract: LLM assistants often produce more answers than humans can review before users see them. Most evaluations ask whether an answer is wrong, unsupported, o...

By SangJin Park, Myungsub Choi, Jineok Kim, Minseung Kang

llms benchmarks

arXiv Machine Learning

Sep 10

Online Learning with LLM Experts from Limited Feedback

arXiv:2609.05820v1 Announce Type: new Abstract: We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We...

By Wang Wei, Soumyabrata Pal, Koyel Mukherjee, Franck Dernoncourt, Ryan A. Rossi, Branislav Kveton, Hoda Eldardiry

llms reinforcement-learning

arXiv AI

Sep 10

Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspective

arXiv:2609.07213v1 Announce Type: new Abstract: We observe a phenomenon that current algorithmic research in the field of explainable artificial intelligence primarily pursues better performance on s...

By Yongjin Cui, Xiaohui Fan

llms safety

arXiv AI

Sep 10

SkillAlign: Aligning Skill Interfaces for LLM-based Agents

arXiv:2609.07255v1 Announce Type: new Abstract: Language-model agents increasingly rely on skills: reusable procedural knowledge for reasoning, tool use, and interaction. Existing work studies how sk...

By Shuo Ren, Xiaomian Kang, Jiajun Zhang

llms agents

arXiv AI

Sep 10

CausalVerify: An Execution-Grounded Benchmark for LLM Causal Inference Workflows

arXiv:2609.07944v1 Announce Type: new Abstract: Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recove...

By Yonghong Zhang, Ricardo Correia, Isabel M. Parra, Yong Xie

llms benchmarks

arXiv AI

Sep 10

When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability

arXiv:2609.07987v1 Announce Type: new Abstract: LLM-based digital twins promise to reduce repeated human data collection by generating person- specific responses, yet existing evaluations provide lit...

By Steven Wang, Kyle Hunt, Shaojie Tang, Kenneth Joseph

llms

arXiv AI

Sep 10

Sparks of In Silico Cognitive Science: Theories from Simulated Data Can Generalize to Humans

arXiv:2609.08003v1 Announce Type: new Abstract: Behavioral foundation models have been proposed as stand-ins for human participants across settings, but it is unclear whether theories discovered on t...

By Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby, Eric Schulz, Nathaniel Daw, Thomas L. Griffiths, Suyog H. Chandramouli

llms agents

arXiv AI

Sep 10

A Layered Analysis of Disagreement And Answer Quality in Multi-Agent LLM Debate

arXiv:2609.08016v1 Announce Type: new Abstract: Multi-agent debate, in which several LLMs exchange arguments before answering, is widely assumed to improve answer quality by surfacing genuine disagre...

By Chen Qian

llms agents safety

arXiv AI

Sep 10

Automated Design of Inventory Policy with Large Language Models: An Exploratory Study

arXiv:2609.08071v1 Announce Type: new Abstract: Firms making inventory decisions have access to operational data, optimization tools, and large language models (LLMs). Typically, data characterize th...

By Fenghua Yang, Preet Baxi, Yi Zhang, Stefanus Jasin, Yanzhe Lei, Mo Liu, Parshan Pakiman

llms benchmarks

arXiv Machine Learning

Sep 10

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

arXiv:2609.06107v1 Announce Type: new Abstract: Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which do...

By Hao Liang, Mingrui Chen, Hengyi Feng, Meiyi Qiang, Wentao Zhang

llms reinforcement-learning benchmarks

arXiv AI

Sep 10

Do Dynamic Routers Need Memory? HeRo: History-Aware Routing for Efficient LLM Inference

arXiv:2609.08189v1 Announce Type: new Abstract: Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, ho...

By Hongjin Lin, Wentao Wan, Keze Wang

llms benchmarks

arXiv AI

Sep 10

LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Generation

arXiv:2609.08288v1 Announce Type: new Abstract: Travel survey data are essential for transportation planning and travel behavior analysis, yet collecting large-scale representative samples is costly...

By Zijian Shen, Bin Zhou, Jiguang Wang, Ya Zhao, Jintao Ke

llms

arXiv AI

Sep 10

ACE: Adapter Consolidation across Experts for Parameter-Efficient Fine-Tuning of MoE LLMs

arXiv:2609.06072v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) of mixture-of-experts (MoE) models commonly attaches a separate low-rank adapter to each expert. This expert-w...

By Ahin Lee, Sehyun Yun, Joonha Park, Taesik Gong

llms fine-tuning

arXiv AI

Sep 10

PAGR: Proof-Carrying Algebraic-Geometric Retrieval: A Quiver-, Provenance-, and Sheaf-Theoretic Framework for Grounded LLM Retrieval

arXiv:2609.06127v1 Announce Type: cross Abstract: Retrieval-augmented generation is usually formulated as a statistical information-retrieval problem. Graph-based variants add relational structure, b...

By Xingting Wang, Min Wu

llms rag

arXiv Machine Learning

Sep 10

AI and TCAD for Inverse Design and Defect Discovery: From Simple Machine Learning to LLM

arXiv:2609.07046v1 Announce Type: new Abstract: AI has revolutionized various engineering domains, but its impact on semiconductor device design and defect discovery is still limited, due to limited...

By Hiu Yung Wong

llms multimodal

arXiv Machine Learning

Sep 10

SIM: Subspace Interaction-based Method for Token-Level Text Anomaly Detection

arXiv:2609.08200v1 Announce Type: new Abstract: Token-level text anomaly detection, as an emerging trend of text anomaly detection, moves beyond coarse-grained document-level detection by localizing...

By Kehan Yan, Yue Tan, Qingfeng Chen, Shiyuan Li, Yu Zheng, Yixin Liu

llms rag benchmarks safety

Get the daily briefing