Large language models

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

25,737 stories · RSS feed

arXiv Machine Learning

Jul 1

Addressing Over-Refusal in LLMs with Competing Rewards

arXiv:2606. 31748v1 Announce Type: new Abstract: Safety training on language models often induces over-refusal: improved safety on harmful prompts at the cost of increased refusal on harmless ones.

By Taeyoun Kim, Aviral Kumar

llms reinforcement-learning safety

arXiv Machine Learning

Jul 1

Contextual Slate GLM Bandits with Limited Adaptivity

arXiv:2606. 31449v1 Announce Type: new Abstract: We investigate the contextual slate bandit problem with generalized linear rewards under limited adaptivity.

By Tanmay Goyal, Sukruta Prakash Midigeshi, Gaurav Sinha

llms reinforcement-learning benchmarks

arXiv AI

Jul 1

ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents

arXiv:2606. 31174v1 Announce Type: new Abstract: Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows.

By Kaiwen Xiong, Haonian Ji, Shi Qiu, Zeyu Zheng, Cihang Xie, Xinyu Ye, Huaxiu Yao

llms agents multimodal benchmarks

arXiv AI

Jul 1

KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving

arXiv:2605. 09735v2 Announce Type: replace-cross Abstract: Static-graph LLM decoders provide predictable launches, fixed tensor shapes, and low submission overhead, but online decoding exposes highly irregular KV-cache behavior: request lengths differ, EOS events arrive asynchronously, and logical histories fragment over time.

By Zhiqing Zhong, Zhijing Ye, Jian Zhang, Weijian Zheng, Bolun Sun, Xiaodong Yu

llms efficiency

arXiv AI

Jul 1

Shared Lexical Task Representations Explain Behavioral Variability In LLMs

arXiv:2604. 22027v2 Announce Type: replace-cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed.

By Zhuonan Yang, Jacob Xiaochen Li, Francisco Piedrahita Velez, Eric Todd, David Bau, Michael L. Littman, Stephen H. Bach, Ellie Pavlick

llms

arXiv AI

Jul 1

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching

arXiv:2601. 23088v2 Announce Type: replace-cross Abstract: Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft.

By Zhixiang Zhang, Zesen Liu, Yuchong Xie, Quanfeng Huang, Dongdong She

llms rag agents safety

arXiv AI

Jul 1

Artificial Intelligence in Sports: Insights from a Quantitative Survey among Sports Students in Germany about their Perceptions, Expectations, and Concerns regarding the Use of AI Tools

arXiv:2503. 05785v2 Announce Type: replace-cross Abstract: Generative Artificial Intelligence (AI) tools such as ChatGPT, Copilot, or Gemini have a crucial impact on academic research and teaching.

By Dennis Kraemer, Anja Bosold, Martin Minarik, Cleo Schyvinck, Andre Hajek

llms

arXiv AI

Jul 1

Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles

arXiv:2606. 23672v2 Announce Type: replace Abstract: This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Manipulation Puzzles.

By Prateek Agnihotri, Sanchit Jain, Prabhat Agnihotri, Aditya Prasad, Shubham Jain

llms agents nlp robotics fine-tuning safety

arXiv AI

Jul 1

Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework

arXiv:2605. 24661v2 Announce Type: replace Abstract: LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into the underlying reasoning processes that produce those answers.

By Ali \c{S}enol, Garima Agrawal, Huan Liu

llms benchmarks

arXiv AI

Jul 1

Containment Verification: AI Safety Guarantees Independent of Alignment

arXiv:2605. 09045v2 Announce Type: replace Abstract: Agentic frameworks are the software layer through which AI agents act in the world.

By Royce Moon, Lav R. Varshney

llms agents safety

arXiv AI

Jul 1

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

arXiv:2606. 31825v1 Announce Type: cross Abstract: Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences.

By Junha Jung, Minbyul Jeong, Suhyeon Lim, Sungwook Jung, Jaehoon Yun, Taeyun Roh, Mujeen Sung, Jaewoo Kang

llms nlp reinforcement-learning multimodal benchmarks

arXiv AI

Jul 1

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning

arXiv:2606. 31599v1 Announce Type: cross Abstract: Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medical images, which typically exhibit extremely sparse visual evidence to inform clinical decision-making.

By Kaitao Chen, Weiqian Zhao, Jiamin Wu, Qihao Zheng, Shangquan Sun, Chunfeng Song, Xiaosong Wang, Mu Zhou, Mianxin Liu

llms nlp reinforcement-learning efficiency multimodal benchmarks

arXiv AI

Jul 1

CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs

arXiv:2606. 31309v1 Announce Type: cross Abstract: While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.

By Zhengxing Li, David J. Miller, Guangmingmei Yang, George Kesidis

llms rag

arXiv AI

Jul 1

Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG

arXiv:2606. 30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements.

By Naihao Deng, Yilun Zhu, Joan Nwatu, Clayton Scott, Rada Mihalcea

llms benchmarks safety

arXiv AI

Jul 1

The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning

arXiv:2606. 30875v1 Announce Type: cross Abstract: Foundation model pseudo-labeling - labeling data strictly via zero-shot inference - enables massive scale, but performance is undermined by hallucinations that evade standard thresholds.

By Brent A. Griffin, Jason J. Corso

llms computer-vision fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jul 1

A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization

arXiv:2606. 30775v1 Announce Type: cross Abstract: Enterprise AI agents route user queries to specialized skills by matching queries against natural language skill descriptions.

By Yangqiaoyu Zhou, Mohammad Alqudah, Kwei-Herng Lai, Aaron Halfaker, Yingqi Xiong, Yaar Harari

llms agents benchmarks

arXiv AI

Jul 1

ELEVATE: Designing Human-Centered GenAI Virtual Tutors for Scalable and Inclusive Education

arXiv:2606. 30662v1 Announce Type: cross Abstract: The advent of Generative Artificial Intelligence (GenAI), and in particular Large Language Models (LLMs), is reshaping educational practice, while intensifying ethical debate about its adoption.

By Lorenzo Stacchio, Michele Giordano, Daniele Berardini, Primo Zingaretti, Emanuele Frontoni

llms robotics multimodal safety

arXiv AI

Jul 1

Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA

arXiv:2606. 32002v1 Announce Type: new Abstract: Language models are increasingly taught from synthetic question--answer (QA) supervision: a model generates questions about a document, answers them from the same text, and the resulting pairs are used to fine-tune, distill, or compress knowledge into another model.

By Ekaterina Alimaskina, Denis Shveykin, Gleb Molodtsov, Igor Shalygin, Alexey Kadeishvili, Aleksandr Beznosikov

llms fine-tuning

arXiv AI

Jul 1

An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping

arXiv:2606. 31831v1 Announce Type: new Abstract: High-throughput plant phenotyping now generates image derived datasets far faster than scientists can analyze them.

By Renan Souza, Daniel Rosendo, Kelsey Carter, John Lagergren, Fr\'ed\'eric Suter, Shelaine L. Curd, Gerald A. Tuskan, Rafael Ferreira da Silva, David Weston

llms agents computer-vision efficiency

arXiv AI

Jul 1

Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index

arXiv:2606. 31575v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a powerful tool for propelling Large Language Models (LLMs) beyond imitation-based training towards more robust reasoning capabilities.

By Outongyi Lv, Yanzhao Zheng, Yuanwei Zhang, Zhenghao Huang, Xingjun Wang, Baohua Dong, Hangcheng Zhu, Yingda Chen

llms reinforcement-learning benchmarks

Get the daily briefing