9 citations · 18 across the 34 of their papers we have counts for
43 papers
Loose Lips: Understanding Privacy Leakage in Agentic Dialogue
Soumya Sharma, Ayana Hussain, Heber Hwang Arcolezi +4
As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue has become critical. Privacy lea…
Visual Memory Attacks Can Persist Through The KV Cache
David Dobre, Leo Schwinn, Gauthier Gidel +3
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input continue to steer a model even aft…
Backdoor Decontamination Dynamics in LLM Agents
Gabriel Huang, Abhay Puri, Léo Boisvert +4
Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defender…
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
Shubham Gupta, Nazanin Mohammadi Sepahvand, Abhinav Kumar +6
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate information may not only be exposed through outp…
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3
AI agents acting on behalf of users are constantly making decisions, and for users to trust their agents, those decisions must align with what they actually want. Privacy is an imp…
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Charbel El Feghali, Arkil Patel, Nicholas Meade +3
Open-weight Large Language Models (LLMs) enable scientific progress and broad deployment. However, they make it difficult to control access to sensitive capabilities. Current pract…
Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents
Sina Hajimiri, Masih Aminbeidokhti, Jose Dolz +4
Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume test-time tokens, a cost rarely r…
MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents
Alexander Gurung, Spandana Gella, Alexandre Drouin +3
Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive in…
Mem-: Adaptive Memory through Learning When and What to Generate
Xiaoqiang Wang, Chao Wang, Hadi Nekoei +5
We present Mem-, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory st…
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
Xiangru Jian, Shravan Nayak, Kevin Qinghong Lin +5
Computer-use agents (CUAs) hold great promise for automating complex desktop workflows, yet progress toward general-purpose agents is bottlenecked by the scarcity of continuous, hi…
VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing
Joan Rodriguez, Haotian Zhang, Abhay Puri +14
We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, complex editing, and visual understanding.…
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
Ahmed Masry, Megh Thakkar, Patrice Bechard +9
Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrie…
Grounding Computer Use Agents on Human Demonstrations
Aarash Feizi, Shravan Nayak, Xiangru Jian +14
Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web…
Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
Suyuchen Wang, Tianyu Zhang, Ahmed Masry +4
GUI grounding, the task of mapping natural-language instructions to pixel coordinates, is crucial for autonomous agents, yet remains difficult for current VLMs. The core bottleneck…
DRBench: A Realistic Benchmark for Enterprise Deep Research
Amirhossein Abaskohi, Tianyi Chen, Miguel Muñoz-Mármol +11
We introduce DRBench, a benchmark for evaluating AI agents on complex, open-ended deep research tasks in enterprise settings. Unlike prior benchmarks that focus on simple questions…
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
Rabiul Awal, Mahsa Massoud, Aarash Feizi +10
We present WebMMU, a multilingual benchmark that evaluates three core web tasks: (1) website visual question answering, (2) code editing involving HTML/CSS/JavaScript, and (3) mock…
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Ahmed Masry, Abhay Puri, Masoud Hashemi +13
Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) ha…
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA
Rishabh Maheshwary, Masoud Hashemi, Khyati Mahajan +5
Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This hinders a model's capacity to process and reas…
Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Juan A. Rodriguez, Haotian Zhang, Abhay Puri +12
Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-qua…
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
Amirhossein Abaskohi, Amrutha Varshini Ramesh, Shailesh Nanisetty +6
We introduce AgentAda, the first LLM-powered analytics agent that can learn and use new analytics skills to extract more specialized insights. Unlike existing methods that require…
SafeArena: Evaluating the Safety of Autonomous Web Agents
Ada Defne Tur, Nicholas Meade, Xing Han Lù +6
LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinf…
StarFlow: Generating Structured Workflow Outputs From Sketch Images
Patrice Bechard, Chao Wang, Amirhossein Abaskohi +6
Workflows are a fundamental component of automation in enterprise platforms, enabling the orchestration of tasks, data processing, and system integrations. Despite being widely use…
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
Shravan Nayak, Xiangru Jian, Kevin Qinghong Lin +11
Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enhance computer workflows. While existing…
PairBench: Are Vision-Language Models Reliable at Comparing What They See?
Aarash Feizi, Sai Rajeswar, Adriana Romero-Soriano +4
Understanding how effectively large vision language models (VLMs) compare visual inputs is crucial across numerous applications, yet this fundamental capability remains insufficien…