# zzli2022/Awesome-System2-Reasoning-LLM

Latest Advances on System-2 Reasoning

Repository: https://github.com/zzli2022/Awesome-System2-Reasoning-LLM
Canonical: https://ross.abutalabs.com/products/awesome-system2-reasoning-llm
Language: Python
License Family: other
Topics: benchmark, macro-action, mcts, o1, prm, r1, reasoning, rl, self-improve, slow-fast, system-2, o3
Last push: 2025-06-08T15:02:47+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 25, release rhythm 35, longevity 40
- inputs: {"age_days": 570, "days_push": 451, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1353, forks 80 (observed 2026-08-28T04:04:28.605750+00:00)

## What it is
A curated awesome-list tracking the latest advances in System-2 reasoning for large language models, accompanying a survey paper on reasoning LLMs. It organizes papers, projects, and benchmarks across topics like o1 replication, process reward models, MCTS, reinforcement learning, and self-improvement.

## Use cases
- find papers on system-2 reasoning in LLMs
- track o1 and o3 replication projects
- research process reward models and MCTS for reasoning
- find benchmarks for evaluating reasoning LLMs
- survey reinforcement learning methods for LLM reasoning
- keep up with slow-fast reasoning research

## When to choose
- you need a curated, up-to-date reading list on reasoning LLMs
- you are writing a survey or literature review on LLM reasoning
- you want to discover open-source o1-style reasoning model reproductions

## When to avoid
- you need runnable software or code, not a paper list
- you want a single tool rather than a collection of resources
- you need non-reasoning-related LLM topics

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-training, benchmarking
- domain: large-language-models, artificial-intelligence, tutorials, awesome-lists
- platform: python
- tags: awesome-list, reasoning-llm, system-2-reasoning, survey-paper, mcts, process-reward-models, reinforcement-learning, o1-replication, chain-of-thought

## Member repositories
- zzli2022/Awesome-System2-Reasoning-LLM (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:28.605750+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:42:07.403604+00:00, confidence not recorded.
  - readme: https://github.com/zzli2022/Awesome-System2-Reasoning-LLM (fetched 2026-08-28T04:04:28.605750+00:00, sha 8523b37aa1dd)
- Data as of 2026-08-30T08:39:29.467469+00:00.