Large language models

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

21,000 stories · RSS feed

arXiv AI

Jul 21

OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration

arXiv:2505. 11765v5 Announce Type: replace-cross Abstract: Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications.

By Shijun Li, Hilaf Hasson, Joydeep Ghosh

llms agents

arXiv AI

Jul 21

RealDESED: A Real-World Domestic Sound Event Detection Benchmark

arXiv:2607. 16736v1 Announce Type: cross Abstract: This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes.

By Florian Schmid, Paul Primus, Alexander Fichtinger, Tara Jadidi, Tobias Morocutti, Gerhard Widmer

llms benchmarks

arXiv Machine Learning

Jul 21

Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models

arXiv:2606. 20959v2 Announce Type: replace Abstract: Language models may encode both outdated facts and their newer replacements.

By Elias Hossain, Sourav Saha, Tasfia Nuzhat Ornee, Sanjeda Sara Jennifer, Umesh Chandra Biswas, Shubhashis Roy Dipta, Rajib Rana, Niloofar Yousefi

llms benchmarks

arXiv AI

Jul 21

SGA: Plug&Play Geometric Verification for Educational Video Synthesis

arXiv:2607. 18116v1 Announce Type: new Abstract: Recent work leverages Large Language Models (LLMs) to generate executable code for pedagogical animations using libraries such as Manim.

By Lopez Jhon, Hinojosa Carlos, Ghanem Bernard

llms agents benchmarks

arXiv AI

Jul 21

Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory

arXiv:2607. 17545v1 Announce Type: new Abstract: Language agents depend on memory across interactions.

By Qingcan Kang, Mingyang Liu, Shixiong Kai, Kaichao Liang, Zhentao Tang, Yuqi Cui, Tao Zhong, Mingxuan Yuan

llms agents benchmarks safety

arXiv AI

Jul 21

LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models

arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.

By Zeyu Xu, Xingzhong Hou, Pengkai Guo, Siling Lin, Xiao Xu, Menghua Zhai, Haoyu Chen, Yunke Zhang, Fei Huang

llms rag multimodal benchmarks

arXiv AI

Jul 21

Stress Testing Concept Erasure with Large Language Model Agents

arXiv:2607. 17890v1 Announce Type: new Abstract: Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment.

By Yuyang Xue, Feng Chen, Zhihua Liu, Edward Moroshko, Jingyu Sun, Steven McDonagh, Sotirios A. Tsaftaris

llms agents

arXiv Machine Learning

Jul 21

The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Convergent Category Geometry in Small Language Models

arXiv:2607. 16741v1 Announce Type: new Abstract: B\"urger et al.

By Francesco Karim Vicidomini

llms

arXiv AI

Jul 21

Environment-free Synthetic Data Generation for API-Calling Agents

arXiv:2607. 16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories.

By Seanie Lee, Sanjoy Chowdhury, Chao Jiang, Cheng-Yu Hsieh, Ting-Yao Hu, Alexander T Toshev, Oncel Tuzel, Raviteja Vemulapalli

llms agents fine-tuning benchmarks

arXiv AI

Jul 21

Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training

arXiv:2603. 00454v3 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) enable fine-tuning large language models to approximate reward-proportional posteriors, but they remain prone to mode collapse, manifesting as prefix collapse and length bias.

By Xi Wang, Wenbo Lu, Shengjie Wang

llms fine-tuning safety

arXiv AI

Jul 21

The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems

arXiv:2607. 17947v1 Announce Type: new Abstract: Existing AI measurement frameworks quantify cognitive capability, task automation, or catastrophic risk, but none measure autonomous agency: the extent to which a system behaves in a self-directed way.

By Samuel Presgraves

llms agents benchmarks safety

arXiv AI

Jul 21

Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict

arXiv:2605. 14473v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is usually evaluated by whether the final answer is correct.

By Yihang Chen, Pin Qian, Su Wang, Sipeng Zhang, Huan Xu, Shuhuai Lin, Xinpeng Wei

llms rag safety

arXiv AI

Jul 21

Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference

arXiv:2604. 23724v3 Announce Type: replace-cross Abstract: Expressway video anomaly detection is essential for safety management.

By Xiaowei Mao, Bowen Sui, Weijie Zhang, Yawen Yang, Shengnan Guo, Shilong Zhao, Jiaqi Lin, Tingrui Wu, Youfang Lin, Huaiyu Wan

llms multimodal safety

arXiv AI

Jul 21

Let the Data Decide: Supervision Analysis, Capability Trade-offs, and Adaptive Objective Routing in Continued Pre-Training via Off-Policy Distillation

arXiv:2607. 16246v1 Announce Type: cross Abstract: Off-policy distillation is now central to large language model pre-training, yet how training data, objective parameterization, and model capabilities interact remains poorly characterized.

By Jiangan Yuan, Zhixuan Li, Han Xu

llms efficiency

arXiv AI

Jul 21

Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation

arXiv:2607. 18029v1 Announce Type: cross Abstract: Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata.

By Blake G. Fitch, Cato Elia Kurtz

llms agents fine-tuning benchmarks safety data-engineering

arXiv AI

Jul 21

ClawBench: Can AI Agents Complete Everyday Online Tasks?

arXiv:2604. 08523v2 Announce Type: replace-cross Abstract: AI agents may be able to assist with emails and documents, but can they reliably complete everyday online workflows on real websites?

By Yuxuan Zhang, Yubo Wang, Yipeng Zhu, Penghui Du, Junwen Miao, Xuan Lu, Zhuofeng Li, Xingwei Qu, Zhengkang Guo, Yuanzhe Shen, Dingjie Song, Han Zhou, Tuney Zheng, Xian Wu, Hao Yu, Songcheng Cai, Yi Lu, Yunzhuo Hao, Minyi Lei, Liang Chen, Kai Zou, Huifeng Yin, Wendong Xu, Dongfu Jiang, Ping Nie, Jiaheng Liu, Wenhu Chen, Kelsey R. Allen

llms agents benchmarks

arXiv AI

Jul 21

When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models

arXiv:2512. 04124v4 Announce Type: replace-cross Abstract: Frontier language models increasingly participate in conversations about distress and mental health, yet the mechanisms that generate anthropomorphic self narratives remain unclear.

By Afshin Khadangi, Hanna Marxen, Amir Sartipi, Igor Tchappi, Gilbert Fridgen

llms reinforcement-learning safety

arXiv AI

Jul 21

GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models

arXiv:2511. 07457v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks.

By Jiarui Feng, Donghong Cai, Yixin Chen, Muhan Zhang

llms fine-tuning safety

arXiv AI

Jul 21

CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs

arXiv:2603. 27958v2 Announce Type: replace Abstract: Analogical reasoning tests a fundamental aspect of human cognition: mapping the relation from one pair of objects to another.

By Yongkang Du, Xiaohan Zou, Minhao Cheng, Lu Lin

llms multimodal benchmarks

arXiv AI

Jul 21

mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks

arXiv:2601. 02451v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) suffer from over-smoothing in deep architectures and expressiveness bounded by the 1-Weisfeiler-Leman (1-WL) test.

By Subhankar Mishra

llms benchmarks

Get the daily briefing