collaborators

5 papers

cs.CR2026

The Surface You Test Is Not the Surface That Breaks

Shifat E Arman, Syed Nazmus Sakib, Nafiul Haque +1

Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the agent then executes as if they…

cs.CV2026

Thinking Like a Botanist: Challenging Multimodal Language Models with Intent-Driven Chain-of-Inquiry

Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin +4

Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-based adaptive questioning. In pl…

cs.AI2026

PATHWAYS: Evaluating Investigation and Context Discovery in AI Web Agents

Shifat E. Arman, Syed Nazmus Sakib, Tapodhir Karmakar Taton +2

We introduce PATHWAYS, a benchmark of 250 multi-step decision tasks that test whether web-based agents can discover and correctly use hidden contextual information. Across both clo…

cs.CV2025

Orion: A Unified Visual Agent for Multimodal Perception, Advanced Visual Reasoning and Execution

N Dinesh Reddy, Dylan Snyder, Lona Kiragu +3

We introduce Orion, a visual agent that integrates vision-based reasoning with tool-augmented execution to achieve powerful, precise, multi-step visual intelligence across images,…

cs.CV2025

SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases

Shifat E. Arman, Hasan Muhammad Abdullah, Syed Nazmus Sakib +5

Despite progress in AI-based plant diagnostics, sugarcane farmers in low-resource regions remain vulnerable to leaf diseases due to the lack of scalable, efficient, and interpretab…