[ICML 2026 Spotlight] Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
☆70Jun 3, 2026Updated last month
Alternatives and similar repositories for critique-GRPO
Users that are interested in critique-GRPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Repo for SwS: A Weakness-driven Problem Synthesis Framework in RL for LLM Reasoning☆41Nov 11, 2025Updated 8 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆459Mar 20, 2026Updated 4 months ago
- Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition☆31May 14, 2025Updated last year
- Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"☆65Jan 5, 2026Updated 6 months ago
- ☆47Jun 24, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆17Nov 20, 2024Updated last year
- ☆24Nov 4, 2025Updated 8 months ago
- ☆27Aug 31, 2025Updated 10 months ago
- ☆23Apr 5, 2026Updated 3 months ago
- ☆18Mar 16, 2026Updated 4 months ago
- Reinforcement Learning from Text Feedback☆49Feb 17, 2026Updated 5 months ago
- ☆13Nov 11, 2022Updated 3 years ago
- [ICLR 2026] Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization☆32Mar 6, 2026Updated 4 months ago
- Official Code For EMNLP2025 Findings: {DLPO : Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Le…☆10Dec 25, 2025Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [NeurIPS 2025] RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning☆57Oct 23, 2025Updated 8 months ago
- Agent-RRM: Exploring Reasoning Reward Model for Agents☆70Mar 17, 2026Updated 4 months ago
- ☆18Dec 23, 2025Updated 6 months ago
- Pixels, Patterns, but no Poetry: To See the World like Humans☆18Aug 11, 2025Updated 11 months ago
- ☆42Oct 29, 2024Updated last year
- ☆21May 14, 2026Updated 2 months ago
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆33Aug 4, 2024Updated last year
- ☆32Oct 8, 2025Updated 9 months ago
- [XLLM@ACL2025] Official Code for "Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation"☆22Jul 29, 2025Updated 11 months 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.
- Reinforcement Learning via Self-Distillation (SDPO)☆1,017Jul 1, 2026Updated 2 weeks ago
- Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning☆44Jul 2, 2025Updated last year
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆443Jul 11, 2025Updated last year
- Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training☆54Dec 13, 2025Updated 7 months ago
- This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.☆130Apr 7, 2026Updated 3 months ago
- ☆44Mar 31, 2026Updated 3 months ago
- Official Implementation of Trajectory-Refined Distillation☆26Jun 9, 2026Updated last month
- High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning☆55Jul 23, 2025Updated 11 months ago
- Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).☆51Mar 31, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ICLR 2026] Official repo for "FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting"☆50Oct 9, 2025Updated 9 months ago
- [R]einforcement [L]earning from [M]odel-rewarded [T]hinking - code for the paper "Language Models That Think, Chat Better"☆128Oct 27, 2025Updated 8 months ago
- Reinforcement Learning of Vision Language Models with Self Visual Perception Reward☆175Mar 14, 2026Updated 4 months ago
- Implementation of "PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier"☆17Jun 27, 2025Updated last year
- [preprint] Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning☆19Feb 18, 2026Updated 5 months ago
- [NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models☆58Sep 29, 2025Updated 9 months ago
- Co-evolving policy actors and experience extractors for efficient experience-driven agent RL☆51May 12, 2026Updated 2 months ago