Large language models

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

31,695 stories · RSS feed

arXiv AI

Jun 2

When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs

arXiv:2602. 03554v2 Announce Type: replace-cross Abstract: Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning.

By Bogdan Zagribelnyy, Ivan Ilin, Maksim Kuznetsov, Nikita Bondarev, Mathieu Reymond, Roman Schutski, Thomas MacDougall, Rim Shayakhmetov, Zulfat Miftakhutdinov, Mikolaj Mizera, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov

llms benchmarks

arXiv AI

Jun 2

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

arXiv:2605. 12400v2 Announce Type: replace-cross Abstract: We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories.

By Yuxiao Yang, Xiaoyun Wang, Weitong Zhang

llms efficiency benchmarks

arXiv AI

Jun 2

On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance

arXiv:2606. 00467v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with user-provided instructions.

By Etienne Casanova, Rafal Kocielnik, R. Michael Alvarez

llms rag safety

arXiv AI

Jun 2

Two-Fidelity Best-Action Identification for Stochastic Minimax Tree

arXiv:2606. 01708v1 Announce Type: cross Abstract: We study fixed-confidence best-action identification (BAI) in stochastic minimax trees.

By Peter Chen, Xi Chen

llms reinforcement-learning

arXiv AI

Jun 2

Argument Collapse: LLMs Flatten Long-Form Public Debate

arXiv:2606. 01736v1 Announce Type: cross Abstract: As LLMs are increasingly used to draft public-facing arguments, they may flatten public debate by repeatedly introducing the same polished, plausible arguments.

By Yekyung Kim, Yapei Chang, Chau Minh Pham, Mohit Iyyer

llms

arXiv AI

Jun 2

Dive into Waves: Morlet Spectral Transformer for Cross-Subject Emotion Decoding from EEG

arXiv:2606. 00884v1 Announce Type: cross Abstract: We study cross-subject emotion recognition from EEG, a practically important yet challenging problem in brain-computer interfaces.

By Jiaxin Qing, Lexin Li

llms nlp

arXiv AI

Jun 2

Subliminal Learning is a LoRA Artifact

arXiv:2606. 00831v1 Announce Type: new Abstract: Subliminal learning is a phenomenon where language models can transmit behavioral traits to other models through seemingly innocuous data (Cloud et al.

By Todd Nief, Harvey Yiyun Fu, Mark Muchane, Ari Holtzman

llms fine-tuning

arXiv AI

Jun 2

PBT-Bench: Benchmarking AI Agents on Property-Based Testing

arXiv:2605. 15229v3 Announce Type: replace-cross Abstract: Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a described issue.

By Lucas Jing, Xinqi Wang, Liao Zhang, Simon S. Du

llms agents benchmarks

arXiv AI

Jun 2

MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition

arXiv:2606. 00708v1 Announce Type: new Abstract: Automated data science is a structured model-selection problem.

By Yifan Bao, Xinyu Xi, Xinyu Liu, Wen Ge, Lei Jiang, Kevin Zhang, Raad Khraishi, Yihao Ang, Anthony K. H. Tung, Lukasz Szpruch, Hao Ni

llms agents reinforcement-learning

arXiv AI

Jun 2

Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification

arXiv:2606. 01160v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used with formal interactive theorem provers such as Lean 4.

By Shihao Ji, Haotao Tan, Zihui Song, Mingyu Li

llms reinforcement-learning safety

arXiv AI

Jun 2

On Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral

arXiv:2606. 00272v1 Announce Type: new Abstract: The FETCH classifier generates follow-up questions to help refine the best match for the applicant's legal problem, using a low-cost ensemble of LLMs.

By Quinten Steenhuis, Jacqueline Harvey

llms

arXiv Machine Learning

Jun 2

FLaG: Fine-Grained Latent Grouping for Hallucination Detection

arXiv:2606. 00301v1 Announce Type: new Abstract: Hallucinations in large language models (LLMs) arise from heterogeneous failure mechanisms, making reliable detection difficult for any single global uncertainty score.

By Wentao Ye, Liyao Li, Zhiqing Xiao, Muzhi Zhu, Jiaqi Hu, Zhanming Shen, Xiaomeng Hu, Sean Du, Haobo Wang

llms benchmarks safety

arXiv AI

Jun 2

HomeFlow: A Data Flywheel for Smart Home Agent Training with Verifiable Simulation

arXiv:2606. 01230v1 Announce Type: new Abstract: Large language model agents are moving beyond text-only interaction toward physical-world control, with smart homes as a representative domain.

By Yi Gu, Huacan Wang, Shuo Zhang, Yuqing Hou, Lei Xue, Weipeng Ming, Chen Liu, Fangzhou Yu, Kuan Li, Ronghao Chen, Sen Hu, Xiaofeng Mou, Yi Xu

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 2

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

arXiv:2603. 19005v2 Announce Type: replace-cross Abstract: Data science plays a critical role in transforming complex data into actionable insights across numerous domains.

By An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, Ashish Kundu, Jayanth Srinivasa, Mingyi Hong, Rui Zhang, Tianxi Li, Galin Jones, Jie Ding

llms agents benchmarks

arXiv Machine Learning

Jun 2

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

arXiv:2606. 00566v1 Announce Type: new Abstract: As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party content, their attack surface expands well beyond what users type.

By Mohammed Sameer Syed (University of Arizona), Rozhin Yasaei (University of Arizona)

llms agents safety

arXiv Machine Learning

Jun 2

Latent Diffusion Pretraining for Crystal Property Prediction

arXiv:2606. 00776v1 Announce Type: new Abstract: Fast and accurate prediction of crystal properties is a central challenge in new materials design.

By Shrimon Mukherjee, Kishalay Das, Partha Basuchowdhuri, Pawan Goyal, Niloy Ganguly

llms diffusion fine-tuning

arXiv AI

Jun 2

Learning to Remember, Learn, and Forget in Attention-Based Models

arXiv:2602. 09075v3 Announce Type: replace-cross Abstract: In-Context Learning (ICL) in transformers acts as an online associative memory and is believed to underpin their high performance on complex sequence processing tasks.

By Djohan Bonnet, Jamie Lohoff, Jan Finkbeiner, Elidona Skhikerujah, Emre Neftci

llms benchmarks

arXiv AI

Jun 2

AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis

arXiv:2606. 02403v1 Announce Type: cross Abstract: Systematic reviews rely on forest plots to synthesise quantitative evidence across biomedical studies, but generating them remains a fragmented and labour-intensive process.

By Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi, Paul Flanagan, Ois\'in Redmond, Joao Bettencourt-Silva, Gurdeep Mannu, Spiros Denaxas, Rui Bebiano Da Providencia E Costa, Anya Belz, Yufang Hou

llms

arXiv Machine Learning

Jun 2

An Algebraic View of the Expressivity of Recurrent Language Models

arXiv:2606. 01765v1 Announce Type: cross Abstract: What formal languages can a recurrent neural language model recognize?

By Franz Nowak, Ryan Cotterell, Reda Boumasmoud

llms efficiency

arXiv AI

Jun 2

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

arXiv:2606. 01770v1 Announce Type: cross Abstract: Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on fixed offline benchmarks.

By Zewen Liu, Zhan Shi, Yisi Sang, Bing He, Minhua Lin, Tianxin Wei, Dakuo Wang, Benoit Dumoulin, Wei Jin, Hanqing Lu

llms agents benchmarks

Get the daily briefing