Large language models

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

26,872 stories · RSS feed

arXiv AI

Jun 16

Robust Dual-Signal Fusion: Hybrid Neuro-Symbolic Gating with Compressed Chain-of-Thought Refinement for Irony Detection in Social Media Texts

arXiv:2606. 16845v1 Announce Type: cross Abstract: Large Language Models (LLMs) natively default to literal semantic interpretations, making zero-shot irony detection a persistent challenge.

By Ankit Bhattacharjee, Krityapriya Bhaumik

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jun 16

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

arXiv:2605. 01973v2 Announce Type: replace-cross Abstract: Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes.

By Luo Ji, Qi Qin, Ningyuan Xi, Teng Chen, Qingqing Gu, Hongyan Li

llms fine-tuning

arXiv AI

Jun 16

AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining

arXiv:2505. 23878v2 Announce Type: replace-cross Abstract: Optimizing pretraining data composition is pivotal for LLM generalization.

By Jing Ma, Chenhao Dang, Mingjie Liao

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 16

Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation

arXiv:2606. 14945v1 Announce Type: new Abstract: The autoresearch pattern enables autonomous experimentation by having a large language model (LLM) iteratively modify code to optimize a target metric.

By Faramarz Jabbarvaziri

llms agents benchmarks

arXiv AI

Jun 16

GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking

arXiv:2606. 15788v1 Announce Type: cross Abstract: Large Language Models (LLMs) constitute pivotal components within the AI-dominated information technology ecosystem.

By Aman Anifer, Vignesh Kumar Kembu, Vishnu M, Antonino Nocera, Vinod P., Amal Murali PK, Akshay S Rajan

llms robotics safety

arXiv AI

Jun 16

LLM-Assisted Stance Detection in Scientific Discourse: A Test Case in Bayesian Cognitive Science

arXiv:2606. 15566v1 Announce Type: cross Abstract: Qualitative coding is central to social science, but expert annotation is difficult to scale.

By Eyup Engin Kucuk, Tarik Kelestemur, \"Omer Da\u{g}lar Tanrikulu

llms

arXiv AI

Jun 16

Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains

arXiv:2604. 02343v2 Announce Type: replace-cross Abstract: We study the compression of LLM-generated text across lossless and lossy regimes, characterizing a compression-compute frontier where more compression is possible at the cost of more compute.

By Roy Rinberg, Annabelle Michael Carrell, Simon Henniger, Nicholas Carlini, Keri Warr

llms fine-tuning benchmarks

arXiv AI

Jun 16

Service-Induced Congestion in Memory-Constrained LLM Serving

arXiv:2606. 15555v1 Announce Type: cross Abstract: In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with every generated token.

By Ruicheng Ao, Jing Dong, Gan Luo, David Simchi-Levi

llms efficiency

arXiv Machine Learning

Jun 16

ExpRL: Exploratory RL for LLM Mid-Training

arXiv:2606. 17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model.

By Violet Xiang, Amrith Setlur, Chase Blagden, Nick Haber, Aviral Kumar

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Jun 16

When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic Underwriting

arXiv:2606. 16465v1 Announce Type: new Abstract: AI agents can now take irreversible actions in operational systems, but agent-caused losses are still not clearly assigned, priced, or transferred.

By Binyan Xu, Xilin Dai, Fan Yang, Kehuan Zhang

llms agents

arXiv Machine Learning

Jun 16

GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

arXiv:2606. 16771v1 Announce Type: new Abstract: As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities.

By Haotian Liu, Yihao Liu, Jingwei Ni, Siyuan Huang, Xinpeng Liu, Pengyu Cheng, Jiajun Song, Ruijin Ding, Junfeng Li, Zhechao Yu, Mengyu Zhou, Hongteng Xu, Xiaoxi Jiang, Guanjun Jiang

llms agents reinforcement-learning safety

arXiv Machine Learning

Jun 16

How Post-Training Shapes Biological Reasoning Models

arXiv:2606. 16517v1 Announce Type: new Abstract: Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins.

By Lukas Fesser, Hanlin Zhang, Michelle M. Li, Eric Wang, Bryan Perozzi, Shekoofeh Azizi, Sham M. Kakade, Marinka Zitnik

llms reinforcement-learning fine-tuning multimodal

arXiv AI

Jun 16

Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains

arXiv:2606. 15841v1 Announce Type: new Abstract: Large language model (LLM) systems increasingly use uncertainty signals to allocate limited computation across verification, test-time scaling, tool execution, and other selective-compute decisions.

By Jinlong Yang

llms

arXiv AI

Jun 16

Guiding Federated Graph Recommendation with LLM-encoded knowledge

arXiv:2606. 15277v1 Announce Type: cross Abstract: Graph-based recommender systems are highly effective at extracting collaborative signals from user--item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy.

By Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen, Van Ho-Long, Thanh Trung Huynh, Zhao Ren

llms rag benchmarks safety

arXiv AI

Jun 16

Honeypot Protocol

arXiv:2604. 13301v1 Announce Type: cross Abstract: Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection.

By Najmul Hasan

llms

arXiv AI

Jun 16

Phase-Aware Guidance Injection for Recurrent MAPPO in Assembly-Line Disruption Recovery

arXiv:2606. 16330v1 Announce Type: new Abstract: Disruption recovery in industrial assembly lines requires timely decisions under machine faults, worker absence, and emergency orders.

By Xin Huang, Yongcai Wang, Fengyi Zhang, Zhikun Tao, Yunjun Han, Naiqi Wu

llms safety

arXiv AI

Jun 16

LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control

arXiv:2606. 16802v1 Announce Type: new Abstract: Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over complex interfaces, and feedback-driven parameter adjustment.

By Anqi Zou, Han Deng, Chengyu Zhang, Junquan Hu, Yu Wang, Yuxiang Xing, Aokai Zhang, Hanling Zhang, Zhaoyang Liu, Ben Fei, Zhihui Wang, Wanli Ouyang

llms agents multimodal benchmarks safety

arXiv AI

Jun 16

Evaluating the Robustness of Proof Autoformalization in Lean 4

arXiv:2606. 14867v1 Announce Type: cross Abstract: Proof autoformalization aims to translate a mathematical informal proof written in natural language into a formal proof in a formal language such as Lean~4.

By Zhengtao Gui, Sheng Yang, Zhouxing Shi

llms benchmarks

arXiv AI

Jun 16

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

arXiv:2606. 15258v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources.

By Jierui Zhang, Siyuan Tan, Xinhang Li, Longzhuangzhi Lin, Dailin Li, Chengfeng Gu, Xinping Li, Yaxian Hao, Shengjia Liang, Yuxiang Ren, Wenhao Liu

llms benchmarks

arXiv AI

Jun 16

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

arXiv:2602. 06486v2 Announce Type: replace Abstract: Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility.

By Lanbo Lin, Jiayao Liu, Tianyuan Yang, Li Cai, Yuanwu Xu, Lei Wei, Sicong Xie, Guannan Zhang

llms agents safety

Get the daily briefing