Projects

Explore my research projects and practical applications of optimization and machine learning.

Tool-Augmented LLMs for Operations Management

SmartAPS is an agentic conversational system that transforms how operations planners interact with Advanced Planning Systems. Using tool-augmented LLMs with retrieval-based API selection, it enables natural language what-if and why-not scenario analyses, reducing consultant dependency from days to hours.

Generative AI For Optimization Modeling

More details coming soon.

HybridMind: AI-Human Collaboration for Algorithmic Ideation

More details coming soon.

Robust MAS Design

More details coming soon.

Beating SOTA on Large Scale CVRP

More details coming soon.

Bayan Algorithm: Rigorous Community Detection via Exact Modularity Optimization

Challenge: Community detection algorithms typically use heuristics with no optimality guarantees. Our research shows that sub-optimal partitions are disproportionately dissimilar to any optimal partition, even when their modularity scores are near-maximum.

Technical Innovation: Bayan solves the NP-hard modularity maximization problem using a specialized Branch-and-Cut scheme with novel triangular constraint-based cuts. For a violated node triple (i,j,k), we partition the solution space via two distinct cut types:

  • Left cut (equating membership): xij + xik + xjk = 0
  • Right cut (disallowing co-membership): xij + xik + xjk ≥ 2

This disjunction enables efficient exploration of the feasible space through targeted branching strategies (e.g., supernode replacement for left subproblems).

Empirical Results:

  • Accuracy: Consistently ranked top-3 out of 30 algorithms for retrieving planted communities (highest AMI on LFR/ABCD benchmarks)
  • Quality: Best median performance across 5 metrics (description length, coverage, performance, average conductance, well-clusteredness) on 1000 networks
  • Speed: 3.7× faster than Gurobi IP and 15.5× faster than igraph on average; solved instances unsolvable by alternatives within 4-hour limits
  • Critical finding: Standard heuristics achieved global optimality in only 43.9% of 104 networks analyzed