sylvain-wei / 24-Game-ReasoningLinks
超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1
☆23Updated 3 months ago
Alternatives and similar repositories for 24-Game-Reasoning
Users that are interested in 24-Game-Reasoning are comparing it to the libraries listed below
Sorting:
- MPO: Boosting LLM Agents with Meta Plan Optimization☆63Updated 4 months ago
- ☆136Updated last month
- IKEA: Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent☆60Updated 2 months ago
- ☆57Updated 2 weeks ago
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆51Updated last month
- [ACL'25] We propose a novel fine-tuning method, Separate Memory and Reasoning, which combines prompt tuning with LoRA.☆67Updated last month
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 8 months ago
- Official code implementation for the ACL 2025 paper: 'CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis'☆27Updated last month
- ☆33Updated last month
- ☆102Updated 7 months ago
- ☆64Updated last month
- [ICML 2025] Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search☆103Updated last month
- Open source code of the paper: "OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain"☆67Updated 6 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆115Updated 8 months ago
- A trainable user simulator☆34Updated 2 weeks ago
- SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis☆81Updated last month
- Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning☆201Updated this week
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆145Updated 6 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆74Updated 3 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆109Updated 5 months ago
- The GitHub repository for the paper "Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning" accepte…☆19Updated last year
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆22Updated 5 months ago
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆49Updated 8 months ago
- Test-time preferenece optimization (ICML 2025).☆147Updated 2 months ago
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆33Updated last year
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆79Updated last month
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆55Updated 7 months ago
- Code for ICLR 2024 paper "CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets"☆57Updated last year
- Official implementation of the paper "From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large L…☆50Updated last year
- MARFT stands for Multi-Agent Reinforcement Fine-Tuning. This repository implements an LLM-based multi-agent reinforcement fine-tuning fra…☆49Updated last month