McGill-NLP / the-markovian-thinkerLinks
Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"
☆335Updated 2 months ago
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"☆251Updated 2 months ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆358Updated 7 months ago
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆560Updated 4 months ago
- SSRL: Self-Search Reinforcement Learning☆204Updated 5 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆259Updated last week
- Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.☆531Updated last month
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆599Updated this week
- Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research☆519Updated last week
- ☆321Updated 4 months ago
- Demystifying Reinforcement Learning in Agentic Reasoning☆155Updated 3 months ago
- Official Project Page for Web World Models (https://arxiv.org/abs/2512.23676)☆76Updated 3 weeks ago
- Latent Collaboration in Multi-Agent Systems☆723Updated this week
- codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆736Updated last month
- ☆227Updated 11 months ago
- ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.☆604Updated last month
- MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents☆547Updated last week
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆88Updated 10 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆168Updated 5 months ago
- Data recipes and robust infrastructure for training AI agents☆84Updated this week
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆102Updated 4 months ago
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆236Updated 3 months ago
- benchmark and evaluate generative research synthesis☆108Updated this week
- Repo for "Adaptation of Agentic AI"☆572Updated this week
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆92Updated last month
- LIMI: Less is More for Agency☆159Updated 3 months ago
- ☆80Updated 3 months ago
- ☆133Updated this week
- Repo2Run is an LLM-based agent that automates environment configuration by generating error-free Dockerfiles for Python repositories.☆151Updated 2 months ago
- Data Synthesis for Deep Research Based on Semi-Structured Data☆193Updated last month
- accompanying material for sleep-time compute paper☆118Updated 8 months ago