Cover Image

MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gurung, Alexander, Gella, Spandana, Drouin, Alexandre, Laradji, Issam H., Taslakian, Perouz, Pardinas, Rafael
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
by: Abaskohi, Amirhossein, et al.
Published: (2024)

Mem-$π$: Adaptive Memory through Learning When and What to Generate
by: Wang, Xiaoqiang, et al.
Published: (2026)

DRBench: A Realistic Benchmark for Enterprise Deep Research
by: Abaskohi, Amirhossein, et al.
Published: (2025)

AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
by: Abaskohi, Amirhossein, et al.
Published: (2025)

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
by: Wang, Suyuchen, et al.
Published: (2025)

A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches
by: Sahu, Gaurav, et al.
Published: (2024)

Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization
by: Sahu, Gaurav, et al.
Published: (2023)

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
by: Masry, Ahmed, et al.
Published: (2025)

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
by: Masry, Ahmed, et al.
Published: (2025)

StarFlow: Generating Structured Workflow Outputs From Sketch Images
by: Bechard, Patrice, et al.
Published: (2025)

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
by: Nayak, Shravan, et al.
Published: (2025)

When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR
by: Züfle, Maike, et al.
Published: (2026)

IntentGPT: Few-shot Intent Discovery with Large Language Models
by: Rodriguez, Juan A., et al.
Published: (2024)

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
by: Patil, Vaidehi, et al.
Published: (2025)

InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
by: Sahu, Gaurav, et al.
Published: (2024)

SafeArena: Evaluating the Safety of Autonomous Web Agents
by: Tur, Ada Defne, et al.
Published: (2025)

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks
by: Rodriguez, Juan, et al.
Published: (2024)

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
by: Monteiro, João, et al.
Published: (2024)

PairBench: Are Vision-Language Models Reliable at Comparing What They See?
by: Feizi, Aarash, et al.
Published: (2025)

Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA
by: Maheshwary, Rishabh, et al.
Published: (2025)

TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
by: Meier, Dominik, et al.
Published: (2025)

RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
by: Monteiro, Joao, et al.
Published: (2024)

Learning to Reason for Long-Form Story Generation
by: Gurung, Alexander, et al.
Published: (2025)

CHIRON: Rich Character Representations in Long-Form Narratives
by: Gurung, Alexander, et al.
Published: (2024)

WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
by: Awal, Rabiul, et al.
Published: (2025)

The Mosaic Memory of Large Language Models
by: Shilov, Igor, et al.
Published: (2024)

Learning to Defer for Causal Discovery with Imperfect Experts
by: Clivio, Oscar, et al.
Published: (2025)

LitLLM: A Toolkit for Scientific Literature Review
by: Agarwal, Shubham, et al.
Published: (2024)

An Open and Reproducible Deep Research Agent for Long-Form Question Answering
by: Yamada, Ikuya, et al.
Published: (2025)

Apriel-1.5-OpenReasoner: RL Post-Training for General-Purpose and Efficient Reasoning
by: Pardinas, Rafael, et al.
Published: (2026)

StarVector: Generating Scalable Vector Graphics Code from Images and Text
by: Rodriguez, Juan A., et al.
Published: (2023)

Lightweight Latent Reasoning for Narrative Tasks
by: Gurung, Alexander, et al.
Published: (2025)

LitLLMs, LLMs for Literature Review: Are we there yet?
by: Agarwal, Shubham, et al.
Published: (2024)

ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
by: Masry, Ahmed, et al.
Published: (2025)

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
by: Kaneko, Masahiro, et al.
Published: (2025)

AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
by: Li, Yishan, et al.
Published: (2026)

SSLR: A Semi-Supervised Learning Method for Isolated Sign Language Recognition
by: Algafri, Hasan, et al.
Published: (2025)

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation
by: Qiao, Yuxuan, et al.
Published: (2025)

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
by: Yao, Yi, et al.
Published: (2026)

FinDeepResearch: Evaluating Deep Research Agents in Rigorous Financial Analysis
by: Zhu, Fengbin, et al.
Published: (2025)