FROM $f(x)$ AND $g(x)$ TO $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones
☆73Jan 26, 2026Updated 9 months ago
Alternatives and similar repositories for RL-Compositionality
Users that are interested in RL-Compositionality are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆19Feb 9, 2026Updated 9 months ago
- [ICML 2026] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆265Apr 30, 2026Updated 6 months ago
- ☆48Jun 24, 2025Updated last year
- ☆370Jul 29, 2025Updated last year
- [ICML 2026 Spotlight] On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models☆171Jun 8, 2026Updated 5 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.
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆455Jul 11, 2025Updated last year
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆33Mar 2, 2025Updated last year
- Codebase for the paper "A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language"☆11Oct 11, 2024Updated 2 years ago
- [ACL '24] Source code for paper: INTERVENOR : Prompt the Coding Ability of Large Language Models with the Interactive Chain of Repairing☆28Nov 25, 2024Updated last year
- ☆16Nov 14, 2025Updated last year
- The first high school physics Olympiad benchmark for evaluating (M)LLMs with step-level grading and human-level comparison.☆26Dec 19, 2025Updated 10 months ago
- 6,080-param transformer achieving 100% accuracy on 10-digit addition. Trained from scratch in 10 minutes.☆22Feb 19, 2026Updated 8 months ago
- [Target-SFT] A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design☆13Jun 10, 2026Updated 5 months ago
- ☆28May 8, 2024Updated 2 years 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.
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆188Jul 23, 2025Updated last year
- Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"☆15Sep 25, 2025Updated last year
- Aioli: A unified optimization framework for language model data mixing☆34Jan 17, 2025Updated last year
- [AAAI 2026] ReCode: Reinforced Code Knowledge Editing for API Updates☆26Jul 1, 2025Updated last year
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆365Aug 21, 2026Updated 2 months ago
- ☆15Jun 21, 2026Updated 4 months ago
- Single-pass Adaptive Image Tokenization for Minimum Program Search | What's the Kolmogorov Complexity of an Image?☆47Jul 26, 2025Updated last year
- Official repository of PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective☆29Jun 13, 2026Updated 5 months ago
- Code of EMNLP 2025 paper 'UltraIF: Advancing Instruction Following from the Wild'.☆21Apr 3, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- P1: Mastering Physics Olympiads with Reinforcement Learning☆91Dec 29, 2025Updated 10 months ago
- ☆20Sep 16, 2025Updated last year
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆11Oct 31, 2024Updated 2 years ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆233Nov 27, 2025Updated 11 months ago
- [NeurIPS 2025] TTRL: Test-Time Reinforcement Learning☆1,133Apr 15, 2026Updated 7 months ago
- ☆18Feb 2, 2026Updated 9 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆476Mar 20, 2026Updated 7 months ago
- ☆42Feb 18, 2025Updated last year
- The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''☆113Aug 15, 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.
- ☆13Jul 8, 2024Updated 2 years ago
- A benchmark and open call for valuable, reproducible RL runs.☆32Updated this week
- ☆45Sep 19, 2024Updated 2 years ago
- ☆31Jul 16, 2025Updated last year
- ☆178Dec 13, 2025Updated 11 months ago
- [ICLR 2026] Meta-RL Induces Exploration in Language Agents☆53Feb 1, 2026Updated 9 months ago
- ☆335May 31, 2025Updated last year
Are these results useful?