facebookresearch / sweet_rl
Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
☆140Updated last week
Alternatives and similar repositories for sweet_rl:
Users that are interested in sweet_rl are comparing it to the libraries listed below
- ☆104Updated 2 months ago
- ☆54Updated this week
- ☆188Updated last month
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆162Updated 2 weeks ago
- Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]☆131Updated 4 months ago
- ☆262Updated 2 weeks ago
- Repo of paper "Free Process Rewards without Process Labels"☆138Updated 3 weeks ago
- Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples☆84Updated last week
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆78Updated 3 weeks ago
- ☆111Updated last month
- ☆129Updated last week
- Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling☆95Updated 2 months ago
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆210Updated last week
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"☆131Updated last month
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆161Updated 2 weeks ago
- ☆61Updated 3 months ago
- ☆84Updated last month
- official implementation of paper "Process Reward Model with Q-value Rankings"☆51Updated last month
- Implementation of the Quiet-STAR paper (https://arxiv.org/pdf/2403.09629.pdf)☆53Updated 7 months ago
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆170Updated last week
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆115Updated 2 weeks ago
- Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"☆54Updated 4 months ago
- ☆117Updated 9 months ago
- Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆76Updated 3 weeks ago
- AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reaso…☆75Updated 2 weeks ago
- ☆144Updated 3 months ago
- AWM: Agent Workflow Memory☆252Updated 2 months ago
- Framework and toolkits for building and evaluating collaborative agents that can work together with humans.☆70Updated last month
- Benchmarking LLMs with Challenging Tasks from Real Users☆219Updated 5 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆89Updated 5 months ago