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 AI

Jun 2

ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents

arXiv:2606. 02568v1 Announce Type: new Abstract: Clinical practice is not the selection of an answer from enumerated options: a physician gathers heterogeneous information incrementally and commits to sequential, irreversible decisions under uncertainty.

By Yuxing Lu, Yushuhong Lin, Wenqi Shi, J. Ben Tamo, Xukai Zhao, Jinzhuo Wang, May Dongmei Wang

llms agents benchmarks

arXiv Machine Learning

Jun 2

KG-FairDiff: Knowledge Graph-Guided Prompt Refinement for Demographically Fair Text-to-Image Generation

arXiv:2606. 01282v1 Announce Type: cross Abstract: Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inherit from training data (rendering women, people of colour, older adults, and non-Western cultures as under-represented or caricatured) become a population-level harm at deployment scale.

By Farbod Davoodi, Seyed Reza Tavakoli Shiyadeh, Pooria Safaei, Sana Harighi, Parsa Gholami, Amirali Amini, Kimia Vanaei, Emad Firoozi, Parham Abed Azad, Babak Khalaj, Siavash Ahmadi, Amir Hossein Payberah, Mohammad Hossein Rohban, Soheil Kolouri, Ali Diba

llms diffusion safety

arXiv AI

Jun 2

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

arXiv:2606. 02355v1 Announce Type: new Abstract: Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency.

By Zhongyu He, Yuanfan Li, Fei Huang, Tianyu Chen, Siyuan Chen, Xingyang Li, Meng Hsuan Yu, Xiangrong Liu, Leyi Wei, Lu Pan, Ke Zeng, Xunliang Cai

llms agents reinforcement-learning efficiency

arXiv AI

Jun 2

ASE-26: a curriculum for agentic software engineering as a discipline

arXiv:2606. 01152v1 Announce Type: cross Abstract: The work of a professional software engineer has begun to consist, increasingly, of directing agents rather than writing code, and the empirical evidence for the shift is now several years deep.

By Mikael Gorsky

llms agents

arXiv AI

Jun 2

Implicit Geographic Inference in LLM Medical Triage: Language-Driven Disparities in Emergency Recommendations

arXiv:2606. 01204v1 Announce Type: cross Abstract: We investigate whether large language models produce different medical triage recommendations for identical symptoms based solely on the language of the patient prompt.

By Qi Han Wong

llms

arXiv AI

Jun 2

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning

arXiv:2606. 01991v1 Announce Type: new Abstract: As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the risk of power-seeking.

By Lichao Wang, Zhaoxing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai

llms agents reinforcement-learning safety

arXiv Machine Learning

Jun 2

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

arXiv:2606. 01923v1 Announce Type: cross Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations.

By Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min

llms efficiency safety

arXiv AI

Jun 2

Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

arXiv:2606. 01393v1 Announce Type: cross Abstract: Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems.

By Minglai Yang, Xinyan Velocity Yu, Pengyuan Li, Xinyu Guo, Zhenting Qi, Konwoo Kim, Longtian Ye, Xiaolong Luo, Jinhe Bi, Henry Zhang, Haris Riaz, Xuan Zhang, Yunze Xiao, Bangya Liu, Tom Tang, Yunfei Zhao, Qunshu Lin, Zihan Wang, Minghao Liu, Michael Lingzhi Li, Yilun Du, Jesse Thomason, Rogerio Feris, Alex Pentland, Zexue He

llms computer-vision multimodal benchmarks

arXiv AI

Jun 2

Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners

arXiv:2606. 01810v1 Announce Type: new Abstract: Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning.

By Zheng Lu, Mingqi Gao, Qinlei Xie, Wanqi Zhong, Hanwen Cui, Heng Cao, Zirui Song, Yifan Yang, Chong Luo, Bei Liu, Yiming Li

llms agents robotics multimodal benchmarks

arXiv AI

Jun 2

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory

arXiv:2606. 01385v1 Announce Type: cross Abstract: Software architecture design is a critical yet inherently complex and knowledge-intensive phase that requires balancing competing quality attributes and adapting to evolving requirements.

By Ruiyin Li, Yiran Zhang, Xiyu Zhou, Yangxiao Cai, Peng Liang, Weisong Sun, Jifeng Xuan, Zhi Jin, Yang Liu

llms rag agents

arXiv AI

Jun 2

Joint Agent Memory and Exploration Learning via Novelty Signals

arXiv:2606. 01528v1 Announce Type: new Abstract: In open-ended environments, exploration is fundamental for autonomous agents, yet current language model agents struggle with this.

By Shizuo Tian, Xiaohong Weng, Rui Kong, Yuxuan Chen, Guohong Liu, Yuebing Song, Jiacheng Liu, Yuchen Li, Dawei Yin, Ting Cao, Yunxin Liu, Yuanchun Li

llms agents

arXiv AI

Jun 2

S-SPPO: Semantic-Calibrated Self-Play Preference Optimization

arXiv:2606. 01561v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO).

By Xiwen Chen, Wenhui Zhu, Jingjing Wang, Peijie Qiu, Zhipeng Wang, Huayu Li, ZhengXiao He, Xuanzhao Dong, Prayag Tiwari, Mingkun Xu, Yujian Xiong, Feng Luo, Abolfazl Razi, Brendan Hogan Rappazzo, Anderson Schneider, Yuriy Nevmyvaka

llms reinforcement-learning

arXiv Machine Learning

Jun 2

Deep Learning for Remote Sensing to Improve Flood Inundation Mapping

arXiv:2606. 02310v1 Announce Type: cross Abstract: Flooding is the most pervasive natural disaster worldwide.

By Yogesh Bhattarai, Vijay Chaudhary, Wai Lim Kim, Sanjib Sharma

llms diffusion

arXiv AI

Jun 2

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

arXiv:2606. 00914v1 Announce Type: new Abstract: LLM agents increasingly act after consuming ranked external information streams such as social feeds, search results, retrieval contexts, and email queues, yet safety evaluations almost always test the model or the user prompt in isolation, never the upstream ranker that decides what the agent reads just before it acts.

By Rana Muhammad Usman

llms agents safety

arXiv AI

Jun 2

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models

arXiv:2606. 01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination.

By Zhiqing Ma, Zhonghao Xu, Dong Yu, Chen Kang, Changliang Li, Pengyuan Liu

llms agents multimodal benchmarks safety

arXiv Machine Learning

Jun 2

G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

arXiv:2606. 01873v1 Announce Type: new Abstract: LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning.

By Yuhan Wang, Yibo Ding, Yutong Ye, Mufan Zhao, Wenbo Zhang, Ruijie Wang, Jianxin Li

llms rag fine-tuning multimodal benchmarks safety

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

RadioMaster: Multi-Agent System for Autonomous Radio Signal Generation

arXiv:2606. 01862v1 Announce Type: cross Abstract: Translating user intents into physical radio signals represents the critical yet notoriously tedious final step in wireless prototyping, as it requires intricate knowledge of physical layer details and presents immense implementation challenges.

By Jiazhen Lei, Tianze Cao, Yuxin Sha, Sihan Wang, Bingbing Wang, Fengyuan Zhu, Zeming Yang, Xiaohua Tian

llms agents benchmarks

arXiv AI

Jun 2

PropLLM: Propagation-Aware Scene Reconstruction for Network Fault Diagnosis

arXiv:2606. 00582v1 Announce Type: new Abstract: Network faults propagate layer by layer along topology and protocol dependencies, yet operations systems typically observe only symptomatic alerts at the tail end of propagation chains, where distinct root-cause faults may produce highly similar end-point symptoms.

By Zongzong Wu, Ming Zhao, Fengxiao Tang, Nei Kato

llms multimodal safety

arXiv AI

Jun 2

A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems

arXiv:2606. 00138v1 Announce Type: new Abstract: Finite element analysis (FEA) is the most important numerical approach for solid mechanics.

By Titu Ranjan Sarker, Muhammed Jawaad Zulqernine, Ling Yue, Shaowu Pan, Chenxi Wang, Shiyao Lin

llms agents

Get the daily briefing