Elad Sharony

Ph.D. student, Electrical and Computer Engineering, Technion

Research intern, NVIDIA Research

I am a Ph.D. student at the Technion, advised by Prof. Shie Mannor, and a research intern at NVIDIA Research. My research is on reinforcement learning and LLM agents: how AI systems learn from interaction and feedback, and how they plan and search efficiently, from robotics to software engineering.

Previously, I was a research intern at the Bosch Center for AI, worked as a control engineer at Intel, and earned a B.Sc. in Mechanical Engineering from the Technion, summa cum laude.

Publications

Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair

Elad Sharony, Ido Greenberg, Jialin Song, Shie Mannor, Gal Chechik, Eli Meirom

Under review

We learn to prioritize proposed edits using execution feedback and edit text, making LLM code-repair search more efficient.

Project arXiv Code coming soon

VLM-Guided Experience Replay

Elad Sharony, Tom Jurgenson, Orr Krupnik, Dotan Di Castro, Shie Mannor

Under review

A method that utilizes pre-trained Vision-Language Models to semantically score and prioritize experiences in the replay buffer, significantly boosting sample efficiency in off-policy RL.

Project arXiv Code coming soon

Learning Multiple Initial Solutions to Optimization Problems

Elad Sharony, Heng Yang, Tong Che, Marco Pavone, Shie Mannor, Peter Karkus

ICRA 2026

A learning method that predicts multiple initial solutions with a single network, helping local optimizers avoid poor local minima in robot control and autonomous driving.

Project arXiv Code

Teaching

Teaching assistant: Control Theory · Control System Design · Control Systems 1Technion
Project supervision: Robotic knot-tying skills · Reinforcement learning in Isaac SimTechnion

Service

Reviewer: CoRL 2025 · ICLR 2026 · ICML 2026 · NeurIPS 2026
Technical editor: Reinforcement Learning: Foundations by Shie Mannor, Yishay Mansour, and Aviv TamarCambridge University Press, 2026