sdc17/SwiReasoning

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

[ICML'26] Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"

[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

A very simple GRPO implement for reproducing r1-like LLM thinking.

[NeurIPS 2026] State of Thought Enables Endogenous Reasoning

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Repo for paper "Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability"

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

A series of technical report on Slow Thinking with LLM