Profile picture

PhD student at MIT CSAIL


· AI for math and science
· Neurosymbolic reasoning
· PL for LLM agents

E-mail: zli11010@mit.edu     X (Twitter): @zli11010
Google Scholar       LinkedIn       GitHub

Welcome! I’m Zed, a first-year PhD student at MIT CSAIL advised by Prof. Armando Solar-Lezama. Previously, I completed my undergrad and MEng at MIT, majoring in computer science and physics. My main research interests are machine learning and formal methods for math and science. I am also interested in programming frameworks for LLM-based agents. I am generously supported by the MIT Presidential Fellowship.

Select publications

, , ,
EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
In NeurIPS, 2025.
EnCompass is a programming framework for adding inference-time scaling to general programs containing LLM calls. While the Python interpreter executes a program linearly from start to finish, EnCompass can backtrack to a previous location in the program and fork the runtime into multiple parallel copies, searching for the best outcome using a user-specified search strategy.
pdfarXivposterblogGitHub
, ,
When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
In ICML, 2024.
Focusing on deterministic sparse-reward environments, we show theoretically and empirically that RL performance gain from skills (temporal abstractions) is worse in environments where solutions to states are less compressible in the information-theoretic sense. Further theoretical results show that using unexpressive skills such as macroactions provably worsen RL performance in certain environments.
pdfarXivposterGitHub
, , , ,
Predictive Chemistry Augmented with Text Retrieval
In EMNLP, 2023.
TextReact augments predictive chemistry with texts retrieved from the literature. For a given chemistry input, the retrieval model retrieves relevant texts, and the predictor uses both the original input and retrieved texts to output predictions. On reaction condition recommendation and one-step retrosynthesis, TextReact outperforms state-of-the-art deep-learning chemistry models by 58.4% and 13.6–15.7%, respectively.
pdfarXivGitHub
, , , ,
LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
In MATH-AI Workshop at NeurIPS, 2022.
LEMMA learns a hierarchy of abstractions to enhance RL for mathematical reasoning. It augments Expert Iteration with an abstraction step, where solutions found so far are rewritten in terms of new higher-level actions, which then become available to solve new problems. LEMMA increases the performance and generalization of an RL agent on equation solving and fraction simplification.
pdfarXivGitHub