Large language models

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

31,384 stories · RSS feed

arXiv Machine Learning

Jun 3

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit

arXiv:2501. 02173v2 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy.

By Huixue Zhou, Hengrui Gu, Xi Liu, Kaixiong Zhou, Mingfu Liang, Yongkang Xiao, Srinivas Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

llms rag

arXiv AI

Jun 3

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.

By Zhiyuan Liu, Yicun Yang, Yaojie Zhang, Junjie Chen, Chang Zou, Qingyuan Wei, Shaobo Wang, Yichen Zhu, Linfeng Zhang

llms diffusion efficiency

arXiv Machine Learning

Jun 3

RogueMerge: Robust and Unified Attacks against LLM Model Merging

arXiv:2606. 03344v1 Announce Type: cross Abstract: Model merging composes specialized capabilities into a single LLM by aggregating task vectors sourced from unverified public platforms, exposing a critical supply-chain attack surface: Because any malicious behavior can be encoded into a task vector, and merging grants third-party vectors direct write access to model weights, an attacker-provided task vector can enable or amplify diverse downstream threats.

By Jinghuai Zhang, Yetian He, Kunlin Cai, Han Zhao, Fnu Suya, Yuan Tian

llms

arXiv AI

Jun 3

DMF: A Deterministic Memory Framework for Conversational AI Agents

arXiv:2606. 03463v1 Announce Type: new Abstract: Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons.

By Matteo Stabile, Enrico Zimuel

llms agents nlp efficiency benchmarks

arXiv Machine Learning

Jun 3

WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization

arXiv:2603. 04956v2 Announce Type: replace Abstract: This paper considers the problem of converting a given dense linear layer to low precision.

By Egor Lifar, Semyon Savkin, Or Ordentlich, Yury Polyanskiy

llms efficiency benchmarks

arXiv AI

Jun 3

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

arXiv:2605. 27762v2 Announce Type: replace Abstract: We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience.

By Yuchen Guo, Junli Gong, Weicheng Wang, Hongmin Cai, Yiu-ming Cheung, Weifeng Su

llms agents robotics fine-tuning multimodal

arXiv AI

Jun 3

Reproducibility is the New Copyleft: Defining AGI-oriented Reproducible Builds

arXiv:2606. 03019v1 Announce Type: cross Abstract: Copyleft, as implemented in licenses such as the GNU General Public License, was a legal hack that used copyright to guarantee user freedom by tying the availability of source code to every act of distribution.

By Masayuki Hatta

llms agents

arXiv AI

Jun 3

NetKV: Network-Aware Decode Instance Selection for Disaggregated LLM Inference

arXiv:2606. 03910v1 Announce Type: cross Abstract: Disaggregated LLM inference forces the KV cache to traverse the datacenter network before decoding begins, so transfer time enters directly into the Time to First Token (TTFT) budget.

By Mubarak Adetunji Ojewale

llms efficiency

arXiv AI

Jun 3

Large Byte Model: Teaching Language Models About Compiled Code

arXiv:2606. 02834v1 Announce Type: cross Abstract: Malware analysis starts with the raw bytes of an executable program, and tools to "lift" these to higher-level representations, such as assembly, are expensive and subject to error.

By Florian St\"ortz, Catalin-Andrei Stan, Alexandru Dinu, Sandra Servia-Rodr\'iguez, Mihaela Gaman, Calin Miron, Edward Raff

llms nlp

arXiv Machine Learning

Jun 3

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

arXiv:2606. 03458v1 Announce Type: new Abstract: Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows.

By Lorenz K. Muller, Philippe Bich, Chiara Boretti, Hyun-Min Chang, Jiawei Zhuang, Lukas Cavigelli

llms efficiency benchmarks

arXiv Machine Learning

Jun 3

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning

arXiv:2606. 03234v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has become the dominant approach for improving mathematical reasoning in large language models, yet current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.

By Ziyue Wang, Aomufei Yuan, Yongfu Zhu, Shuai Dong, Wenpu Liu, Yiran Yao, Weichu Xie, Yuqi Xu, Caoyuan Ma, Wenqi Shao, Xiaoying Zhang, Nan Duan, Jiaqi Wang

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 3

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs

arXiv:2606. 02628v1 Announce Type: new Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal is strongest.

By Aizierjiang Aiersilan

llms efficiency benchmarks safety

arXiv AI

Jun 3

Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation

arXiv:2604. 17220v2 Announce Type: replace-cross Abstract: Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management.

By Jiuyun Jiang, Yuecheng Hong, Bo Yang, Jin Yang, Guangxin Jiang, Xiaomeng Guo, Guang Xiao

llms agents

arXiv AI

Jun 3

Toward Training Superintelligent Software Agents through Self-Play SWE-RL

arXiv:2512. 18552v3 Announce Type: replace-cross Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.

By Yuxiang Wei, Zhiqing Sun, Emily McMilin, Jonas Gehring, David Zhang, Gabriel Synnaeve, Daniel Fried, Lingming Zhang, Sida Wang

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 3

AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification

arXiv:2606. 03031v1 Announce Type: new Abstract: Structured financial audit verification is difficult for language-model agents because correctness depends on structured evidence rather than text alone.

By Yan Wang, Xuguang Ai, Jaisal Patel, Xueqing Peng, Fengran Mo, Yupeng Cao, Haohang Li, Mingyu Cao, Lingfei Qian, V\'ictor Guti\'errez-Basulto

llms agents

arXiv AI

Jun 3

LLMs, Reasoning and Plagiarism

arXiv:2601. 02380v5 Announce Type: replace-cross Abstract: Recent reports claim that Large Language Models (LLMs) derive new science and exhibit human-level general intelligence.

By Elchanan Mossel

llms

arXiv AI

Jun 3

ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models

arXiv:2510. 09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches.

By Wenbin Guo, Xin Wang, Jiaoyan Chen, Lingbing Guo, Zhao Li, Zirui Chen

llms rag nlp efficiency benchmarks

arXiv AI

Jun 3

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining

arXiv:2509. 22468v2 Announce Type: replace-cross Abstract: High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce.

By Boshra Ariguib, Mathias Niepert, Andrei Manolache

llms rag diffusion fine-tuning multimodal benchmarks

arXiv AI

Jun 3

Typhoon: Towards an Effective Task-Specific Masking Strategy for Pre-trained Language Models

arXiv:2303. 15619v2 Announce Type: replace-cross Abstract: The choice of \emph{which} tokens to mask is a central, under-examined design decision in masked language modeling (MLM).

By Muhammed Shahir Abdurrahman, Hashem Elezabi, Bruce Changlong Xu

llms fine-tuning

arXiv AI

Jun 3

Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement

arXiv:2605. 11954v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in social science as scalable measurement tools for converting unstructured text into variables that can enter standard empirical designs.

By Jinyuan Wang, Ningyuan Deng, Yi Yang

llms efficiency

Get the daily briefing