jwliao-ai / MARFTLinks
MARFT stands for Multi-Agent Reinforcement Fine-Tuning. This repository implements an LLM-based multi-agent reinforcement fine-tuning framework for general agentic tasks, providing a foundational MARFT framework.
☆35Updated 2 weeks ago
Alternatives and similar repositories for MARFT
Users that are interested in MARFT are comparing it to the libraries listed below
Sorting:
- ☆114Updated 4 months ago
- ☆32Updated 3 months ago
- Natural Language Reinforcement Learning☆89Updated 5 months ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆95Updated 2 months ago
- MPO: Boosting LLM Agents with Meta Plan Optimization☆56Updated 3 months ago
- ☆47Updated 5 months ago
- Implementation of the ICML 2024 paper "Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning" pr…☆102Updated last year
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆89Updated last week
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆65Updated last month
- Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆91Updated 3 months ago
- official implementation of paper "Process Reward Model with Q-value Rankings"☆59Updated 4 months ago
- ☆49Updated 3 weeks ago
- Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)☆142Updated 7 months ago
- Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling☆104Updated 4 months ago
- [ICLR 2025] Benchmarking Agentic Workflow Generation☆94Updated 3 months ago
- ☆30Updated 7 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆105Updated 7 months ago
- This is the code of MMOA-RAG.☆53Updated 3 weeks ago
- How to create rational LLM-based agents? Using game-theoretic workflows!☆67Updated 3 months ago
- This is the official implementation for paper "PENCIL: Long Thoughts with Short Memory".☆45Updated 3 weeks ago
- ☆16Updated 2 months ago
- ☆45Updated 3 months ago
- ☆59Updated 10 months ago
- [NeurIPS 2024] Agent Planning with World Knowledge Model☆139Updated 5 months ago
- ☆62Updated 2 months ago
- ☆47Updated 3 months ago
- ☆104Updated last month
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆58Updated 2 months ago
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆48Updated 6 months ago
- ☆69Updated 6 months ago