Shibo Hao

Ph.D. student at UCSD

square.jpg

Hello! I’m Shibo Hao, a Ph.D. student at UC San Diego, advised by Zhiting Hu. My research is funded by the Bloomberg Fellowship. Previously, I received my B.S. in Computer Science from Peking University.

My research goal is to push the boundaries of machine reasoning. My work includes building a system-2 reasoning framework using world-model planning (Reasoning via Planning, Pandora), training LLMs to reason with reinforcement learning (OREO, FoR), augmenting LLMs with external tools (ToolkenGPT), and exploring reasoning in latent space (COCONUT). I also maintain LLM Reasoners, a library for advanced reasoning algorithms in a unified formulation.

News

Dec 21, 2024 Introducing OREO (Offline REasoning Optimization) (Arxiv, Twitter)
Dec 10, 2024 Introducing Coconut 🥥 (Chain of Continuous Thought) (Arxiv, Twitter)
Dec 9, 2024 Honored to receive the Bloomberg Data Science Ph.D. Fellowship!
Jul 10, 2024 LLM Reasoners is accepted to the first Conference of Language Modeling (COLM 2024).
May 24, 2024 Check out 𝒫𝒶𝓃𝒹𝑜𝓇𝒶, our new work towards a general world model 🌎
Nov 17, 2023 Our paper ToolkenGPT received the best paper award at SoCalNLP 2023🎉!
Oct 25, 2023 Reasoning via Planning (RAP) has been featured in State of AI Report 2023.
Oct 8, 2023 Reasoning via Planning (RAP) is accepted to EMNLP 2023!
Sep 22, 2023 Excited to share that ToolkenGPT is accepted to NeurIPS 2023 as an oral presentation!

Selected publications

2024

  1. Preprint
    Offline Reinforcement Learning for LLM Multi-Step Reasoning
    Huaijie Wang*, Shibo Hao*, Hanze Dong, Shenao Zhang, Yilin Bao, Ziran Yang, and Yi Wu
    arXiv preprint arXiv:2412.16145, 2024
    PDF Code
  2. Preprint
    Training Large Language Models to Reason in a Continuous Latent Space
    Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, and Yuandong Tian
    arXiv preprint arXiv:2412.06769, 2024
    PDF Code
  3. Preprint
    Pandora: Towards General World Model with Natural Language Actions and Video States
    Jiannan Xiang*, Guangyi Liu*, Yi Gu*, Qiyue Gao, Yuting Ning, Yuheng Zha, Zeyu Feng, Tianhua Tao, Shibo Hao, Yemin Shi, Zhengzhong Liu, Eric P. Xing, and Zhiting Hu
    arXiv preprint arXiv:2406.09455, 2024
    HTML PDF Code
  4. COLM
    LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
    Shibo Hao*, Yi Gu*, Haotian Luo*, Tianyang Liu, Xiyan Shao, Xinyuan Wang, Shuhua Xie, Haodi Ma, Adithya Samavedhi, Qiyue Gao, Zhen Wang, and Zhiting Hu
    In Conference on Language Model (COLM), 2024
    Also to appear at Large Language Model (LLM) Agents workshop at ICLR 2024
    HTML PDF Code

2023

  1. NeurIPS
    ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
    Shibo Hao, Tianyang Liu, Zhen Wang, and Zhiting Hu
    Advances in Neural Information Processing Systems (oral), 2023
    Best Paper Award at SoCalNLP 2023
    PDF Code Poster Slides
  2. EMNLP
    Reasoning with language model is planning with world model
    Shibo Hao*, Yi Gu*, Haodi Ma, Joshua Jiahua Hong, Zhen Wang, Daisy Zhe Wang, and Zhiting Hu
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
    Featured in State of AI Report 2023
    Also to appear at GenPlan workshop at NeurIPS 2023
    PDF Code Slides