peter-peng-w

MARIO_EVAL

NLProofS

EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search https://arxiv.org/abs/2205.12443

ReST-MCTS

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

OpenDevin

🐚 OpenDevin: Code Less, Make More

RLBench

A large-scale benchmark and learning environment.

llemma_formal2formal

Llemma formal2formal (tactic prediction) theorem proving experiments

llm-continual-learning-survey

Continual Learning of Large Language Models: A Comprehensive Survey

CEB

llmstep

llmstep: [L]LM proofstep suggestions in Lean 4.

Multi-Agents-Debate

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D

set.mm

Metamath source file for logic and set theory

draft_sketch_prove

ntptutorial

Tutorial on neural theorem proving

parsel

Code for Parsel 🐍 - generate complex programs with language models

DotaMath

LightZero

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

MCTS-DPO

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

lean4-maze

maze game encoded in Lean 4 syntax

ChatGLM-Math

llm-reasoners

A library for advanced large language model reasoning

TheoremLlama

This is the official repository for all the code of TheoremLlama

DL4TP

[COLM 2024] A Survey on Deep Learning for Theorem Proving

AgentGym

Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

automatic-lean4-compilation

LLM_Tree_Search

(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training

abel

SOTA Math Opensource LLM

dl4math

Resources of deep learning for mathematical reasoning (DL4MATH).

Step-DPO

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

InstructRAG

InstructRAG: Instructing Retrieval-Augmented Generation with Explicit Denoising

Self-Explore

Self-Explore to avoid ️the p️️it! Improving the Reasoning Capabilities of Language Models with Fine-grained Rewards