Large language models

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

31,091 stories · RSS feed

arXiv AI

Jun 6

LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video

arXiv:2606. 05677v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have advanced image and video understanding and can increasingly handle longer visual inputs.

By Shiqiang Lang, Jing Liu, Haoyang He, Peiwen Sun, Yuanteng Chen, Tao Liu, Lan Yang, Longteng Guo, Honggang Zhang

llms agents robotics multimodal benchmarks

arXiv AI

Jun 6

SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

arXiv:2606. 05563v1 Announce Type: new Abstract: Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context.

By Taewon Yun, Hyeonseong Park, Jeonghwan Choi, Hayoon Park, Yeeun Choi, Hwanjun Song

llms agents benchmarks safety

arXiv AI

Jun 6

Stability vs. Manipulability: Evaluating Robustness Under Post-Decision Interaction in LLM Judges

arXiv:2606. 05384v1 Announce Type: new Abstract: LLM-as-judge evaluation is widely used in benchmarking pipelines, where model outputs are compared and ranked using automated evaluators.

By Srimonti Dutta, Akshata Kishore Moharir

llms benchmarks

arXiv AI

Jun 6

Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)

arXiv:2606. 05901v1 Announce Type: cross Abstract: Large language models (LLMs) have fundamentally transformed the landscape of Natural Language Processing.

By Christopher J. Wedge, Joshua Stutter, Danny Dixon, Jacek Ca{\l}a

llms rag agents nlp fine-tuning benchmarks safety

arXiv AI

Jun 6

Towards Healthy Evolution: Exploring the Role and Mechanisms of Human-Agent Interaction in Self-Evolving Systems

arXiv:2606. 06114v1 Announce Type: new Abstract: Self-evolving agents improve through continual self-play and self-generated learning signals, but autonomous evolution can also cause capability degradation and safety drift.

By Dianxing Shi, Junqi He, Junhao Chen, Bowen Wang, Yuta Nakashima

llms agents reinforcement-learning safety

arXiv AI

Jun 6

Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs

arXiv:2606. 06003v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) fails systematically on queries requiring structural reasoning over interconnected entities.

By Grama Chethan

llms rag

arXiv AI

Jun 6

Multi-Granularity Reasoning for Natural Language Inference

arXiv:2606. 05181v1 Announce Type: cross Abstract: Natural Language Inference (NLI) is a fundamental task in natural language understanding that requires determining the logical relationship between a premise and a hypothesis.

By Chunling Xi, Di Liang

llms benchmarks

arXiv AI

Jun 6

HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes

arXiv:2606. 06390v1 Announce Type: cross Abstract: Indoor scene generation is crucial for robot simulation and modern interior design.

By Wenbo Li, Xiaoliang Ju, Zipeng Qin, Rongyao Fang, Hongsheng Li

llms diffusion robotics multimodal

arXiv AI

Jun 6

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

arXiv:2606. 06087v1 Announce Type: cross Abstract: Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and exposes skill content as plaintext.

By Aofan Yu, Chenyu Zhou, Tianyi Xu, Zihan Guo, Rong Shan, Zhihui Fu, Jun Wang, Weiwen Liu, Yong Yu, Weinan Zhang, Jianghao Lin

llms agents fine-tuning

arXiv AI

Jun 6

Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

arXiv:2606. 06203v1 Announce Type: cross Abstract: Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance.

By Giovanni Dettori, Matteo Boffa, Danilo Giordano, Idilio Drago, Marco Mellia

llms benchmarks

arXiv AI

Jun 6

Ontology-constrained multi-LLM scoring of hypothesis support in the predictive processing literature

arXiv:2606. 05206v1 Announce Type: cross Abstract: Fragmentation is common in interdisciplinary fields with diverse methods and theoretical commitments.

By Hamed Nejat, Alexander Maier, Jesse Spencer-Smith, Andr\'e M. Bastos

llms

arXiv AI

Jun 6

Towards One-to-Many Temporal Grounding

arXiv:2606. 06294v1 Announce Type: cross Abstract: Temporal Grounding (TG) aims to localize video segments corresponding to a textual query.

By Qi Xu, Yue Tan, Shihao Chen, Jiahao Meng, Anna Wang, Shunping Ji, Hao Fei, Jason Li

llms benchmarks

arXiv AI

Jun 6

Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs

arXiv:2606. 05966v1 Announce Type: cross Abstract: Understanding and reasoning about the physical world is the foundation of intelligent behavior, yet state-of-the-art vision-language models (VLMs) still fail at causal physical reasoning, often producing plausible but incorrect answers.

By Tianyi Tang, Zhuoyi Lin, Zeyu Feng, Tianyi Ma, Yew-Soon Ong, Ivor Tsang, Haiyan Yin

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 6

Using street view images and visual LLMs to predict heritage values for governance support: Risks, ethics, and policy implications

arXiv:2601. 06056v2 Announce Type: replace-cross Abstract: During 2025 and 2026, the Energy Performance of Buildings Directive is being implemented in the European Union member states, requiring all member states to have National Building Renovation Plans.

By Tim Johansson, Mikael Mangold, Kristina Dabrock, Anna Donarelli, Ingrid Campo-Ruiz

llms multimodal

arXiv AI

Jun 6

Benchmark Everything Everywhere All at Once

arXiv:2606. 06462v1 Announce Type: new Abstract: Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance.

By Shiyun Xiong, Dongming Wu, Peiwen Sun, Yuang Ai, Bokang Yang, Wencheng Han, Xiao-Hui Li, Xiangyu Yue

llms agents multimodal benchmarks

arXiv AI

Jun 6

AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation

arXiv:2606. 03963v2 Announce Type: replace-cross Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks.

By Roohan Ahmed Khan, Yasheerah Yaqoot, Muhammad Ahsan Mustafa, Dzmitry Tsetserukou

llms agents reinforcement-learning robotics fine-tuning multimodal

arXiv AI

Jun 6

Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

arXiv:2606. 05647v1 Announce Type: new Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools.

By Jingheng Ye, Huiqi Zou, Simon Yu, Weiyan Shi

llms agents safety

arXiv AI

Jun 6

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

arXiv:2606. 05233v1 Announce Type: cross Abstract: Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel.

By Nicholas Saban

llms agents reinforcement-learning multimodal benchmarks safety

arXiv AI

Jun 6

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents

arXiv:2606. 06453v1 Announce Type: new Abstract: Sparse attention is becoming increasingly important for serving large language models (LLMs) as generation lengths continue to grow.

By Zhuoming Chen, Xinrui Zhong, Qilong Feng, Ranajoy Sadhukhan, Yang Zhou, Michael Qizhe Shieh, Zhihao Jia, Beidi Chen

llms agents efficiency

arXiv AI

Jun 6

A Taxonomy of Runtime Faults in Model Context Protocol Servers

arXiv:2606. 05339v1 Announce Type: cross Abstract: MCP (Model Context Protocol) enables LLMs (Large Language Models) to interact with external tools and data sources via a standardized protocol.

By Joshua Owotogbe, Indika Kumara, Willem-Jan van den Heuvel, Damian Andrew Tamburri, Antonio Ken Iannillo, Roberto Natella

llms agents

Get the daily briefing