7 papers
Prefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers
Peter Cho-Ho Lam, Ziyi Wang, Zirui Zhou
Prefix-tuning is a parameter-efficient fine-tuning method for large language models (LLMs) that steers model outputs by prepending task-specific prefix representations to the input…
SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents
Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zirui Zhou
Large language model (LLM)-driven evolutionary search is a powerful paradigm for automated program and algorithm discovery, yet existing systems are largely memoryless: each run ex…
COAgents: Multi-Agent Framework to Learn and Navigate Routing Problems Search Space
Oleksandr Yakovenko, Mahdi Mostajabdaveh, Cheikh Ahmed +4
Although Vehicle Routing Problems (VRP) are essential to many real-world systems, they remain computationally intractable at scale due to their combinatorial complexity. Traditiona…
Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design
Cheikh Ahmed, Mahdi Mostajabdaveh, Zirui Zhou
The integration of Large Language Models (LLMs) into evolutionary frameworks has established a new paradigm for automated heuristic discovery. Despite their promise, these methods…
MASPRM: Multi-Agent System Process Reward Model
Milad Yazdani, Mahdi Mostajabdaveh, Zirui Zhou +1
Inference-time search over multi-agent systems (MAS) wastes compute when it cannot identify which agent's intermediate message advanced progress. We present the Multi-Agent System…
Discrete Optimization of Min-Max Violation and its Applications Across Computational Sciences
Cheikh Ahmed, Mahdi Mostajabdaveh, Samin Aref +1
We introduce the Discrete Min-Max Violation (DMMV) as a general optimization problem which seeks an assignment of discrete values to variables that minimizes the largest constraint…
LLM-Guided Evolution of Symbolic Acceleration Inequality Families for MILP
Milad Yazdani, Mahdi Mostajabdaveh, Samin Aref +1
Integer programming (IP) is central to many combinatorial optimization tasks but remains challenging due to its NP-hard nature. A practical way to improve IP solvers is to manually…