PrAg-PO improves RL-based mathematical reasoning by training models across diverse prompt templates with template-specific format rewards, yielding more diverse reasoning trajectories, stronger benchmark accuracy, and more stable training.
☆13May 12, 2026Updated 6 months ago
Alternatives and similar repositories for PrAg-PO
Users that are interested in PrAg-PO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS '25] FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed☆32Mar 9, 2026Updated 8 months ago
- [arXiv 2026] Learning from Rare Success and Rich Feedback via Reflection-Enhanced Self-Distillation☆20May 21, 2026Updated 5 months ago
- ☆12Feb 6, 2024Updated 2 years ago
- Enhanced Note-Taking Experience with Artificial Intelligence☆14May 18, 2025Updated last year
- A scalable serving system for building and running modular diffusion workflows across GPU clusters.☆12Sep 23, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆14Dec 13, 2017Updated 8 years ago
- This is a Python project for drone area coverage path planning. It implements the Boustrophedon decomposition algorithm to generate effic…☆14Jan 28, 2026Updated 9 months ago
- Pytorch Preprocessing and Training for Open X-Embodiment☆26Jul 13, 2024Updated 2 years ago
- The local-first second brain for your AI agents - measured, self-improving, and gated so it can't leak what you keep private. 13 Claude C…☆32Nov 1, 2026Updated last week
- Official implementation for the IMIG-Dataset generation in paper ContextGen☆11Feb 12, 2026Updated 9 months ago
- The first benchmark that asks code agents to build agents.☆25Jun 4, 2026Updated 5 months ago
- A benchmark-agnostic framework for automatically optimizing LLM agent harnesses☆14Aug 31, 2026Updated 2 months ago
- Large Language Model for Recipe Generation☆12Oct 2, 2024Updated 2 years ago
- ☆15Jul 24, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆51Jan 20, 2025Updated last year
- A GitHub Actions Workflow that will let Claude Code auto-generate documentations for your PRs after getting merged☆19Jun 10, 2025Updated last year
- Code example for pretraining an LLM with vanilla PyTorch training loop☆10Jun 6, 2024Updated 2 years ago
- [COLM 2025: 1st Workshop on the Application of LLM Explainability to Reasoning and Planning] Latent Chain-of-Thought? Decoding the Depth-…☆23Aug 19, 2026Updated 2 months ago
- Official implementation of RP-OPSD for multimodal large language models☆13Aug 13, 2026Updated 3 months ago
- 编译器原理☆17Jul 5, 2019Updated 7 years ago
- ✅ Predicting LLM correctness from model internals☆11Apr 20, 2026Updated 6 months ago
- CaOPD: Calibration-Aware On-Policy Distillation☆18Jun 2, 2026Updated 5 months ago
- ZwZ-v2: RL-trained vision-language models (4B/9B/27B) that connect fine-grained visual evidence across image regions, trained with GRPO o…☆17Oct 31, 2026Updated 2 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- NNUE chess engine in < 64kb☆19Feb 13, 2025Updated last year
- ReflectRL: learning from Golden Negative Trajectories via Reflective-to-Direct reasoning.☆17Jul 4, 2026Updated 4 months ago
- ☆227Oct 30, 2026Updated 2 weeks ago
- [EMNLP 2026] SGSD: Skill-Conditioned Gated Self-Distillation for LLM Reasoning☆14Aug 21, 2026Updated 2 months ago
- CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization☆16May 25, 2026Updated 5 months ago
- ☆14Nov 5, 2026Updated last week
- ☆15Sep 29, 2026Updated last month
- ☆11Oct 9, 2025Updated last year
- LLM Uncertainty Quantification with Attention Chain☆11Mar 24, 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.
- Official Implementation for "CFPO: Counterfactual Policy Optimization for Multimodal Reasoning" (ICML 2026)☆16Jul 13, 2026Updated 4 months ago
- An AI research assistant that helps you rank, compare, and follow up on papers — so you can decide what to read next☆20Mar 31, 2026Updated 7 months ago
- ☆16Sep 4, 2025Updated last year
- ☆12Sep 22, 2024Updated 2 years ago
- Official implementation of OPD-Aha for fine-grained visual perception and multimodal reasoning☆15Sep 16, 2026Updated last month
- [COLM 2026] From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement☆16Jul 26, 2026Updated 3 months ago
- ☆17Apr 17, 2026Updated 6 months ago
Are these results useful?