Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
☆57Sep 19, 2025Updated last year
Alternatives and similar repositories for SPO
Users that are interested in SPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning [ICLR26]☆66Apr 11, 2026Updated 7 months ago
- TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25☆108Jun 16, 2025Updated last year
- Official implementation of the paper "PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space"☆18May 6, 2026Updated 6 months ago
- ☆13Jul 19, 2025Updated last year
- ☆73Oct 23, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆19May 7, 2026Updated 6 months ago
- Code for paper: MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs☆14Aug 25, 2026Updated 2 months ago
- ☆17Apr 10, 2025Updated last year
- ☆68Jul 14, 2025Updated last year
- [NeurIPS 2026] "Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory"☆24Sep 26, 2026Updated last month
- ☆65Mar 30, 2026Updated 7 months ago
- An Ultra-Long Output Reinforcement Learning Approach☆23Jul 31, 2025Updated last year
- ☆14Mar 5, 2024Updated 2 years ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆199May 25, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆10May 6, 2025Updated last year
- ☆55Nov 5, 2026Updated 2 weeks ago
- Official Repo for SwS: A Weakness-driven Problem Synthesis Framework in RL for LLM Reasoning☆67Sep 25, 2026Updated last month
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- This is a repository for Junjia's application of universities, the United States☆23Aug 20, 2020Updated 6 years ago
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆30Oct 14, 2025Updated last year
- ArcherCodeR is an open-source initiative enhancing code reasoning in large language models through scalable, rule-governed reinforcement …☆45Aug 6, 2025Updated last year
- ☆167Jan 21, 2025Updated last year
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆456Jul 11, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆84Jun 8, 2026Updated 5 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆166Jun 22, 2026Updated 5 months ago
- Source implementation and dataset for paper "AssoMem Scalable Memory QA with Multi-Signal Associative Retrieval"☆12May 17, 2026Updated 6 months ago
- ☆28Jul 18, 2025Updated last year
- [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time☆87Jun 10, 2025Updated last year
- ☆349May 24, 2025Updated last year
- ☆20May 14, 2025Updated last year
- PreAct: Prediction Enhances Agent's Planning Ability (Coling2025)☆31Dec 12, 2024Updated last year
- ☆11Jan 27, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Short RL☆20Apr 16, 2026Updated 7 months ago
- THOUGHTSCULPT, a general reasoning and search method for complex tasks☆13Dec 13, 2024Updated last year
- ☆29Aug 8, 2025Updated last year
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆25May 6, 2026Updated 6 months ago
- Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI, derived from Ling.☆108Aug 5, 2025Updated last year
- ☆117Sep 13, 2025Updated last year
- [ACL 2026] Enabling Efficient Reasoning in LLMs via Black-box Persuasive Prompting☆23Jan 9, 2026Updated 10 months ago
Are these results useful?