ScalingIntelligence / codemonkeys
☆37Updated 2 months ago
Alternatives and similar repositories for codemonkeys:
Users that are interested in codemonkeys are comparing it to the libraries listed below
- ☆120Updated 3 weeks ago
- EvaByte: Efficient Byte-level Language Models at Scale☆86Updated 3 weeks ago
- ☆115Updated last month
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆167Updated last month
- Small, simple agent task environments for training and evaluation☆18Updated 5 months ago
- ☆48Updated 5 months ago
- ☆28Updated 5 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- ☆54Updated 7 months ago
- Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆58Updated last week
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆170Updated 3 months ago
- SWE Arena☆30Updated 2 weeks ago
- Functional Benchmarks and the Reasoning Gap☆85Updated 6 months ago
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆86Updated last week
- ☆76Updated last week
- Train your own SOTA deductive reasoning model☆83Updated last month
- ☆46Updated last week
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆60Updated 3 weeks ago
- ☆65Updated this week
- Just a bunch of benchmark logs for different LLMs☆119Updated 8 months ago
- ☆33Updated 9 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆33Updated 2 weeks ago
- ☆71Updated 2 months ago
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆102Updated last week
- OpenPipe ART (Agent Reinforcement Trainer): train LLM agents☆77Updated this week
- Repository for the paper Stream of Search: Learning to Search in Language☆144Updated 2 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆15Updated last week
- Code for ExploreTom☆79Updated 4 months ago
- ☆24Updated 3 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆59Updated 6 months ago