Saaduddin Mahmud
Scholar

Saaduddin Mahmud

Google Scholar ID: fMuMcAgAAAAJ
MCICS, University of Massachusetts Amherst
Reinforcement LearningMulti-Agent SystemsAlignmentLLMs
Citations & Impact
All-time
Citations
106
 
H-index
5
 
i10-index
4
 
Publications
20
 
Co-authors
16
list available
Resume (English only)
Academic Achievements
  • Published multiple journal and conference papers, such as 'Causal Explanations for Sequential Decision Making Under Uncertainty' (JAIR, 2025), 'Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models' (AAAI 2026); Obtained several patents, such as 'Dynamic Refinement of Custom Classes Using Zero-Shot Images' (Under review), 'Vehicle Decision Making Using Sequential Information Probing' (US Patent App. 18/429,196).
Research Experience
  • Conducted research work at UMass Amherst, involving multiple research projects such as CoLLAB and Terrarium.
Education
  • PhD - UMass Amherst, Advisor: Shlomo Zilberstein, Major: Computer Science.
Background
  • PhD candidate in Computer Science at UMass Amherst, advised by Shlomo Zilberstein. Research interests include the alignment of agentic systems and using large language models to infer intent from unstructured instructions.