Alternatives and similar repositories for werewolf_arena

Users that are interested in werewolf_arena are comparing it to the libraries listed below

• agentification / RAFA_code
  ☆144Updated last year
• vwxyzjn / summarize_from_feedback_details
  ☆160Updated last year
• waterhorse1 / Natural-language-RL
  Natural Language Reinforcement Learning
  ☆101Updated 6 months ago
• YifeiZhou02 / ArCHer
  Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
  ☆202Updated 9 months ago
• jwhj / OREO
  ☆117Updated last year
• jwliao-ai / MARFT
  ☆77Updated 3 months ago
• Yu-Fangxu / FoR
  [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  ☆120Updated last week
• sanjibanc / agent_prm
  ☆53Updated 11 months ago
• rsshyam / GRPO
  ☆70Updated last year
• microsoft / SmartPlay
  SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …
  ☆145Updated last year
• jonathanmli / Avalon-LLM
  This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'
  ☆139Updated 8 months ago
• abdulhaim / LMRL-Gym
  ☆110Updated last year
• martin-wey / CodeUltraFeedback
  CodeUltraFeedback: aligning large language models to coding preferences (TOSEM 2025)
  ☆73Updated last year
• thu-coai / SPaR
  ☆46Updated 8 months ago
• amazon-science / PAE
  ☆67Updated 11 months ago
• WindyLee0822 / Process_Q_Model
  official implementation of paper "Process Reward Model with Q-value Rankings"
  ☆65Updated last year
• Wenyueh / game_theory
  How to create rational LLM-based agents? Using game-theoretic workflows!
  ☆92Updated 8 months ago
• thunlp / Optima
  Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"
  ☆69Updated last year
• facebookresearch / sweet_rl
  Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
  ☆261Updated 9 months ago
• allenai / ScienceWorld
  ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
  ☆336Updated 2 months ago
• jxhuang0508 / Awesome-LLM-Reasoning-OpenAI-o1
  Awesome LLM papers, news and projects about learning to reason with LLM, OpenAI o1, reasonning techniques, chain-of-thought (COT), Large …
  ☆27Updated last year
• Gen-Verse / CURE
  [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
  ☆149Updated 4 months ago
• MLE-Dojo / MLE-Dojo
  ☆90Updated 3 months ago
• Berkeley-NLP / Agent-Eval-Refine
  Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]
  ☆148Updated last year
• ltzheng / Synapse
  [ICLR 2024] Trajectory-as-Exemplar Prompting with Memory for Computer Control
  ☆67Updated last month
• Asap7772 / understanding-rlhf
  Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…
  ☆32Updated last year
• benchflow-ai / pokemon-gym
  ☆88Updated 7 months ago
• WooooDyy / LLM-Reverse-Curriculum-RL
  Implementation of the ICML 2024 paper "Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning" pr…
  ☆115Updated 2 years ago
• minaek / reward_design_with_llms
  ☆220Updated 2 years ago
• WentseChen / Verlog
  Verlog: A Multi-turn RL framework for LLM agents
  ☆67Updated 3 weeks ago