Retrieval-augmented generation

Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.

6,512 stories · RSS feed

arXiv AI

Jul 1

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

arXiv:2606. 32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions.

By Sergio Hern\'andez-Guti\'errez, Matteo Merler, Ilze Amanda Auzina, Joschka Str\"uber, Ameya Prabhu, Matthias Bethge

llms rag agents efficiency benchmarks

arXiv AI

Jul 1

Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

arXiv:2606. 31570v1 Announce Type: cross Abstract: Masked autoencoding has emerged as a prominent paradigm for self-supervised learning on 3D point clouds, achieving competitive performance across downstream tasks.

By Xu Yan, Huiqun Wang, Chen Wang, Lei Ren, Di Huang

rag

arXiv AI

Jul 1

STEB: Style Text Embedding Benchmark

arXiv:2606. 31741v1 Announce Type: cross Abstract: While semantic embeddings are rigorously evaluated on the Massive Text Embedding Benchmark, the evaluation of style embeddings remains fragmented, with each work relying on their own set of tasks and datasets.

By Rafael Rivera Soto, Anna Wegmann, Cristina Aggazzotti

rag benchmarks

arXiv AI

Jul 1

A Modular Vision-Language-Action Robotics Framework for Indoor Environments

arXiv:2606. 31144v1 Announce Type: cross Abstract: This paper presents an integrated system for the CMU Vision-Language-Action (VLA) Challenge, designed to enable an autonomous agent to perform complex tasks based on natural language instructions.

By Anindya Jana, Snehasis Banerjee, Arup Sadhu, Ranjan Dasgupta

llms rag agents robotics multimodal

arXiv Machine Learning

Jul 1

SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models

arXiv:2606. 32022v1 Announce Type: new Abstract: Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers.

By Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

llms rag

arXiv AI

Jul 1

GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation

arXiv:2603. 26266v3 Announce Type: replace Abstract: Large vision-language models have endowed GUI agents with strong general capabilities for interface understanding and interaction.

By Rui Xie, Zhi Gao, Chenrui Shi, Zirui Shang, Lu Chen, Qing Li

llms rag agents multimodal safety

arXiv AI

Jul 1

HistoriQA-ThirdRepublic: Multi-Hop Question Answering Corpus for Historical Research, Parliamentary Debates from the French Third Republic (1870-1940)

arXiv:2606. 31325v1 Announce Type: new Abstract: We present HistoriQA-ThirdRepublic: a French-language dataset of multi-hop historical questions derived from parliamentary debates and newspapers of the French Third Republic.

By Aur\'elien Pellet (LRE), Julien Perez (EPITA, LRE), Marie Puren (LRE, CJM)

llms rag nlp benchmarks safety

arXiv Machine Learning

Jul 1

Prompting Robot Teams with Natural Language

arXiv:2509. 24575v2 Announce Type: replace-cross Abstract: This paper presents a framework to prompt multi-robot teams with high-level tasks using natural language expressions.

By Eduardo Sebasti\'an, Nicolas Pfitzer, Ajay Shankar, Amanda Prorok

llms rag robotics

arXiv AI

Jul 1

Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism

arXiv:2606. 31222v1 Announce Type: new Abstract: Composed image retrieval requires identifying a target image from a gallery by integrating a reference image with a textual modification instruction.

By Gunho Jung, Jeong-Woo Park, Seon Bin Kim, Seong-Whan Lee

rag

arXiv Machine Learning

Jul 1

Quality-Aware Modulation for Diffusion Transformers

arXiv:2606. 30934v1 Announce Type: new Abstract: Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep.

By Luke Budny, Yuhong Guo, Kevin Cheung

llms rag diffusion

arXiv Machine Learning

Jul 1

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems

arXiv:2605. 01133v3 Announce Type: replace-cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks.

By Lingxi Zhang, Guangtao Zheng, Hanjie Chen

llms rag agents safety

arXiv Machine Learning

Jul 1

The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills

arXiv:2606. 31272v1 Announce Type: cross Abstract: AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents.

By Hongliang Liu, Yuhao Wu, Tung-Ling Li

rag agents benchmarks safety

arXiv Machine Learning

Jul 1

Visualizing High-Dimensional Graph Embeddings via Informed Multi-View Projections

arXiv:2606. 31119v1 Announce Type: new Abstract: Graphs are commonly visualized in 2D, where humans readily interpret spatial relationships, yet such layouts often distort higher-dimensional structure.

By Ya Ji (Khoury College of Computer Sciences, Northeastern University, Seattle), Xuefeng Li (Khoury College of Computer Sciences, Northeastern University, Seattle), Timo Brand (School of Computation, Information and Technology, Technical University of Munich, Heilbronn, Germany), Jacob Miller (School of Computation, Information and Technology, Technical University of Munich, Heilbronn, Germany), Peng Zhang (Khoury College of Computer Sciences, Northeastern University, Seattle), Stephen Kobourov (School of Computation, Information and Technology, Technical University of Munich, Heilbronn, Germany), Yifan Hu (Khoury College of Computer Sciences, Northeastern University, Seattle)

rag

arXiv AI

Jul 1

RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora

arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.

By Hanjun Cho, Jay-Yoon Lee

llms rag benchmarks

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

RCT: A Robot-Collected Touch-Vision-Language Dataset for Tactile Generalization

arXiv:2606. 31694v1 Announce Type: cross Abstract: For robots manipulating open-world objects, tactile representations must generalize to unseen materials.

By Jingbo He, Michael F\"arber, Roberto Calandra

rag robotics multimodal

arXiv AI

Jul 1

Sparsity-Inducing Divergence Losses for Biometric Verification

arXiv:2606. 31664v1 Announce Type: cross Abstract: Performance in face and speaker verification is largely driven by margin-penalty softmax losses such as CosFace and ArcFace.

By Dimitrios Koutsianos, Ladislav Mo\v{s}ner, Yannis Panagakis, Themos Stafylakis

rag efficiency benchmarks

arXiv AI

Jul 1

ASR-Agnostic Multimodal Spectrotemporal Modeling for Early Dementia Detection

arXiv:2606. 30646v1 Announce Type: cross Abstract: Speech recruits the same executive, attentional, and working memory processes underlying instrumental activities of daily living, or IADLs, providing a non-invasive proxy for cognitive assessment.

By Chukwuemeka Ugwu, Oluwafemi Richard Oyeleke

llms rag multimodal benchmarks

arXiv AI

Jul 1

Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Design

arXiv:2606. 28578v1 Announce Type: cross Abstract: Closed-loop materials discovery iterates between proposing candidate structures and evaluating their properties, and property evaluation dominates the cost.

By Sk Md Ahnaf Akif Alvi, Jan Janssen, Danny Perez, Douglas Allaire, Raymundo Arroyave

rag diffusion reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 1

Agentic RAG-VLM: Affordance-Aware Retrieval-Augmented Generation with Self-Reflective Planning for Robotic Grasping

arXiv:2606. 31200v1 Announce Type: new Abstract: Generalizable robotic grasping in cluttered environments is essential for deploying manipulators in unstructured human spaces, yet existing VLM-based methods rely on visual similarity for object matching, neglecting physical affordances such as handle graspability and material fragility, and operate open-loop without spatial reasoning or failure recovery, limiting their effectiveness when objects are densely packed or physically diverse.

By Tao Chen, Lizheng Liu, Jiaxu Wang, Ziyue Jiang, Ruiqi Tian, JiGuang Huo, Zhongxue Gan

llms rag agents robotics multimodal benchmarks

Get the daily briefing