tensor-theorem-prover • Rank 9.0 • Science 54%

First-order logic theorem prover supporting unification with approximate vector similarity

https://github.com/bowang-lab/bioreason • Rank 5.8 • Science 36%

BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model

https://github.com/amazon-science/auto-cot • Rank 9.1 • Science 23%

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

bear • Science 26%

self-refine • Science 54%

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

pal • Science 54%

PaL: Program-Aided Language Models (ICML 2023)

https://github.com/cyzhh/mmos • Science 23%

Mix of Minimal Optimal Sets (MMOS) of dataset has two advantages for two aspects, higher performance and lower construction costs on math reasoning.

icsfsurvey • Science 54%

Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

hourvideo • Science 54%

[NeurIPS 2024] Official code for HourVideo: 1-Hour Video Language Understanding

tme-agent • Science 54%

TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.

https://github.com/baohaoliao/rsd • Science 36%

[ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.