McGill-NLP / the-markovian-thinkerLinks
Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"
☆327Updated last month
Alternatives and similar repositories for the-markovian-thinker
Users that are interested in the-markovian-thinker are comparing it to the libraries listed below
Sorting:
- The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"☆246Updated last month
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆539Updated 3 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆355Updated 6 months ago
- Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research☆483Updated this week
- Demystifying Reinforcement Learning in Agentic Reasoning☆139Updated 2 months ago
- Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.☆519Updated last month
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆249Updated this week
- Latent Collaboration in Multi-Agent Systems☆668Updated last week
- SSRL: Self-Search Reinforcement Learning☆199Updated 4 months ago
- ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.☆450Updated last week
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆499Updated this week
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆87Updated last month
- ☆226Updated 10 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆169Updated 4 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆101Updated 4 months ago
- codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆714Updated 2 weeks ago
- ☆79Updated 3 months ago
- ☆308Updated 3 months ago
- MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents☆531Updated last week
- Repo2Run is an LLM-based agent that automates environment configuration by generating error-free Dockerfiles for Python repositories.☆143Updated last month
- LongCodeZip: Compress Long Context for Code Language Models [ASE2025]☆134Updated last month
- Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)☆455Updated 4 months ago
- ☆93Updated last month
- Repo for "Adaptation of Agentic AI"☆483Updated last week
- ☆126Updated 3 months ago
- Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.☆783Updated last week
- The official implementation of the paper "Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models".☆85Updated 9 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆84Updated 9 months ago
- Data recipes and robust infrastructure for training AI agents☆73Updated last week
- 🧬 The Huxley-Gödel Machine☆317Updated last month