Large language models

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

19,431 stories · RSS feed

arXiv AI

Jul 28

Evaluating RAG for French immigration law: a benchmark and baseline study

arXiv:2607. 24449v1 Announce Type: cross Abstract: International recruitment in France requires navigating a layered legal framework absent from existing legal AI benchmarks.

By Annia Abtout, Julien Delaunay, Monika Ewa Rakoczy

llms rag benchmarks

arXiv AI

Jul 28

A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility

arXiv:2607. 24663v1 Announce Type: cross Abstract: Scientific user facilities accumulate decades of operational knowledge that no single search index covers: electronic logbooks, technical documents, internal wikis, operations chat messages, maintenance records, and live control-system data.

By Rajat Sainju, Dariusz Jarosz, Hairong Shang, Michael Prince, Ryan M. Aydelott, Mathew J. Cherukara, Yine Sun, Michael D. Borland

llms rag agents

arXiv AI

Jul 28

Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty

arXiv:2508. 08992v4 Announce Type: replace Abstract: Real-world decision-making often involves uncertainty expressed in linguistic rather than numerical terms, and Prospect Theory (PT) provides a classic framework for modeling human behavior under such uncertainty.

By Rui Wang, Qihan Lin, Jiayu Liu, Qing Zong, Tianshi Zheng, Dadi Guo, Haochen Shi, Peixuan Han, Weiqi Wang, Yangqiu Song

llms safety

arXiv AI

Jul 28

Knowledge-Centric Agents for Workflow Generation in ComfyUI

arXiv:2607. 15845v2 Announce Type: replace Abstract: Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular compositions.

By Zhendong Li, Lei Sun, Ruibo Ming, He Zhang, Danda Pani Paudel, Luc Van Gool, Jinjin Gu

llms agents fine-tuning

arXiv AI

Jul 28

PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment

arXiv:2508. 05132v3 Announce Type: replace-cross Abstract: As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical.

By Chang Hong, Minghao Wu, Qingying Xiao, Yuchi Wang, Xiang Wan, Guangjun Yu, Benyou Wang, Yan Hu

llms benchmarks safety

arXiv AI

Jul 28

GFLAN: Generative Functional Layouts

arXiv:2512. 16275v2 Announce Type: replace-cross Abstract: Automated floor plan generation lies at the intersection of combinatorial search, geometric constraint satisfaction, and functional design requirements -- a confluence that has historically resisted a unified computational treatment.

By Mohamed Abouagour, Eleftherios Garyfallidis

llms

arXiv AI

Jul 28

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

arXiv:2602. 05547v2 Announce Type: replace-cross Abstract: RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks.

By Shyam Sundhar Ramesh, Xiaotong Ji, Matthieu Zimmer, Sangwoong Yoon, Zhiyong Wang, Haitham Bou Ammar, Aurelien Lucchi, Ilija Bogunovic

llms reinforcement-learning

arXiv AI

Jul 28

From "Help" to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications

arXiv:2602. 18443v2 Announce Type: replace-cross Abstract: Psychosocial online counselling frequently encounters generic subject lines that impede efficient case prioritisation.

By Philipp Steigerwald, Jens Albrecht

llms fine-tuning safety

arXiv AI

Jul 28

SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving

arXiv:2607. 23933v1 Announce Type: cross Abstract: As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces a fundamental tension between resource utilization and interactive tail latency.

By Yihui Zhang (Beihang University), Tianyu Wo (Beihang University), Jinghao Wang (Beihang University), Xiaoyang Sun (University of Leeds), Menghao Zhang (Beihang University), Cangzhou Yuan (Beihang University), Li Li (Beihang University), Chunming Hu (Beihang University), Albert Y. Zomaya (The University of Sydney), Renyu Yang (Beihang University)

llms rag agents

arXiv AI

Jul 28

Agentic Graph Retrieval-Augmented Generation for Auditable Commercial Registry Analysis

arXiv:2605. 18770v2 Announce Type: replace-cross Abstract: Public commercial registries are formally open, yet their practical analysis remains difficult because relevant facts are scattered across millions of records that combine structured metadata, multilingual legal notices, temporal events, and entity aliases.

By Arthur Capozzi, Dirk Helbing

llms rag agents benchmarks

arXiv AI

Jul 28

MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models

arXiv:2607. 22556v1 Announce Type: new Abstract: Continual learning (CL) is essential for small language models (SLMs) to adapt to evolving real-world needs in resource-constrained deployments.

By Dong Li, Yanchi Liu, Xujiang Zhao, Wei Cheng, Zhengzhang Chen, Xintao Wu, Zhong Chen, Chen Zhao, Haifeng Chen

llms

arXiv AI

Jul 28

ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation

arXiv:2607. 22588v1 Announce Type: new Abstract: Modern compute-intensive software must migrate across a changing ecosystem of accelerators, programming APIs, compiler stacks, and portability layers, including CUDA, OpenMP, OpenCL, and OpenMP target offload.

By Samyak Jhaveri, Erel Kaplan, Tom Yotam, Le Chen, Tomer Bitan, Niranjan Hasabnis, Gal Oren

llms agents benchmarks

arXiv AI

Jul 28

StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech

arXiv:2607. 22658v1 Announce Type: new Abstract: Speech-to-speech dialogue models increasingly depend on prosody and interactional nuance to convey social intent, yet benchmarks for these cues remain limited.

By Yuzhe Wang (Electrical and Computer Engineering Department, Johns Hopkins University, Baltimore, USA), Thomas Thebaud (Electrical and Computer Engineering Department, Johns Hopkins University, Baltimore, USA), Jennifer Hu (Department of Cognitive Science, Johns Hopkins University, Baltimore, USA), Jes\'us Villalba-Lopez (Electrical and Computer Engineering Department, Johns Hopkins University, Baltimore, USA), Venkatesh Ravichandran (Amazon AGI, USA), Georgi Tinchev (Amazon Research, UK), Najim Dehak (Electrical and Computer Engineering Department, Johns Hopkins University, Baltimore, USA), Laureano Moro-Vel\'azquez (Electrical and Computer Engineering Department, Johns Hopkins University, Baltimore, USA)

llms benchmarks safety

arXiv AI

Jul 28

HiLLTS: Zero-Shot Hierarchical LLM-Guided Traffic Signal Control for Sustainable Transportation

arXiv:2607. 22691v1 Announce Type: new Abstract: Urban traffic congestion significantly increases fuel consumption, greenhouse gas emissions, and commuter delays, resulting in substantial economic losses and environmental harm in modern cities.

By Yue Ding, Tendai Mukande, Mingming Liu

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 28

MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation

arXiv:2607. 22706v1 Announce Type: new Abstract: This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrieval and the absence of source verification.

By Hyewon Lee, Minkyung Song, Junghyun Oh, Seunghoon Han, Sungsu Lim

llms rag safety

arXiv AI

Jul 28

TopoFE: topology-aware LLM-guided Automated Feature Engineering

arXiv:2607. 23286v1 Announce Type: new Abstract: Automatic feature engineering (AutoFE) for tabular learning can be naturally formulated as a program synthesis problem, where the objective is to discover predictive feature transformations from an exponentially large search space.

By Sha Li, Naren Ramakrishnan

llms benchmarks

arXiv AI

Jul 28

Plato-Bio: verification-first biological novelty screening with temporal rediscovery and structural benchmarks

arXiv:2607. 23975v1 Announce Type: new Abstract: Large language model research agents can connect literature retrieval, analysis code, and manuscript preparation, but coherent output does not establish scientific validity.

By Stefan G. Creadore

llms agents benchmarks safety

arXiv Machine Learning

Jul 28

Hidden Boundary Motion in Transformer Optimization: Function-Space Orthogonalization of Affine Weight and Bias Updates

arXiv:2607. 22927v1 Announce Type: new Abstract: Weights and biases are normally optimized as separate parameter tensors, yet they do not represent separate functions when the input to an affine layer has nonzero mean.

By Zhang Gongyue, Sheng Yixuan, Liu donghan, Wang Zhiyong, Ren Weihong, Liu honghai

llms safety

arXiv AI

Jul 28

Do Diagrams Help Large Language Models Reason? Evidence from Syllogistic Reasoning

arXiv:2607. 23513v1 Announce Type: cross Abstract: Diagrams are widely used to support logical reasoning, and prior studies suggest that representations such as Euler diagrams can improve human reasoning performance.

By Risako Ando, Koji Mineshima

llms

arXiv AI

Jul 28

CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation

arXiv:2607. 23647v1 Announce Type: cross Abstract: Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring preferences, transient intent, and exposure-induced behavior into one profile.

By Gengyu Zhan

llms multimodal benchmarks safety

Get the daily briefing