Alternatives and similar repositories for poe-world

Users that are interested in poe-world are comparing it to the libraries listed below

• jennyzzt / omni
  OMNI: Open-endedness via Models of human Notions of Interestingness
  ☆57Updated 7 months ago
• vmicheli / delta-iris
  Efficient World Models with Context-Aware Tokenization. ICML 2024
  ☆108Updated last year
• ml-jku / LRAM
  A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
  ☆35Updated 10 months ago
• conglu1997 / intelligent-go-explore
  Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
  ☆64Updated 7 months ago
• p-doom / jasmine
  A simple, performant and scalable JAX-based world modeling codebase
  ☆73Updated this week
• Shalev-Lifshitz / MultiAgentVerification
  Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers
  ☆20Updated 6 months ago
• ChenWu98 / algorithmic-creativity
  [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
  ☆70Updated 4 months ago
• facebookresearch / llm-speedrunner
  The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…
  ☆99Updated last month
• Qualcomm-AI-research / codeit
  ☆27Updated last year
• CLAIRE-Labo / EvoTune
  Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
  ☆111Updated last month
• rail-berkeley / SUPE
  This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."
  ☆33Updated 2 months ago
• benpry / why-think-step-by-step
  Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"
  ☆61Updated 5 months ago
• kvfrans / lmpo
  ☆111Updated 2 weeks ago
• BatsResearch / planetarium
  Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL
  ☆58Updated 11 months ago
• facebookresearch / aira-dojo
  AIRA-dojo: a framework for developing and evaluating AI research agents
  ☆92Updated last month
• ConfeitoHS / arcle
  A Gymnasium-based Environment of the Abstraction and Reasoning Corpus (ARC)
  ☆68Updated last year
• maxencefaldor / omni-epic
  OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).
  ☆68Updated 9 months ago
• amazon-science / PAE
  ☆63Updated 6 months ago
• yilundu / ired_code_release
  ☆70Updated last year
• benediktstroebl / agent-evals
  ☆25Updated 3 months ago
• codezakh / DataEnvGym
  A testbed for agents and environments that can automatically improve models through data generation.
  ☆27Updated 6 months ago
• data-for-agents / insta
  Official Repo for InSTA: Towards Internet-Scale Training For Agents
  ☆55Updated 2 months ago
• brantondemoss / GrokkingComplexity
  Code for
  ☆27Updated 9 months ago
• DeckardAgent / deckard
  Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"
  ☆94Updated 2 years ago
• AutonomousAgentsLab / curiousreplay
  Implementations of Curious Replay for model-based adaptation.
  ☆41Updated 2 years ago
• vladisai / PLDM
  ☆40Updated 2 months ago
• google-deepmind / questbench
  ☆28Updated 4 months ago
• sai-prasanna / dreaming_of_many_worlds
  ☆23Updated last year
• complex-reasoning / RPG
  Official implementation of Regularized Policy Gradient (RPG) (https://arxiv.org/abs/2505.17508)
  ☆37Updated last week
• google-deepmind / spectral_ssm
  ☆34Updated last year