facebookresearch / collaborative-reasonerLinks
Source code for the collaborative reasoner research project at Meta FAIR.
☆103Updated 5 months ago
Alternatives and similar repositories for collaborative-reasoner
Users that are interested in collaborative-reasoner are comparing it to the libraries listed below
Sorting:
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆94Updated this week
- Code for ExploreTom☆86Updated 3 months ago
- Train your own SOTA deductive reasoning model☆107Updated 6 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆184Updated 6 months ago
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆75Updated 9 months ago
- accompanying material for sleep-time compute paper☆115Updated 5 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- ☆133Updated 6 months ago
- ☆81Updated last week
- ☆54Updated 10 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆156Updated last month
- ☆77Updated last week
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆59Updated last year
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆116Updated last month
- Verifiers for LLM Reinforcement Learning☆74Updated 5 months ago
- ☆217Updated 7 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆109Updated 5 months ago
- ☆119Updated last year
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 6 months ago
- Analysis code for paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆52Updated last month
- A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.☆168Updated 2 weeks ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated 2 weeks ago
- Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research☆237Updated this week
- ☆123Updated 7 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆52Updated 4 months ago
- Codebase accompanying the Summary of a Haystack paper.☆79Updated last year
- ☆136Updated last month
- ☆56Updated 3 months ago
- Complex Function Calling Benchmark.☆135Updated 8 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆100Updated last month