lamm-mit / PRefLexORLinks
Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning
☆233Updated 8 months ago
Alternatives and similar repositories for PRefLexOR
Users that are interested in PRefLexOR are comparing it to the libraries listed below
Sorting:
- CodeScientist: An automated scientific discovery system for code-based experiments☆300Updated 4 months ago
- ☆172Updated 8 months ago
- ☆79Updated last month
- ☆138Updated last year
- Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)☆122Updated 9 months ago
- Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"☆348Updated 10 months ago
- ☆158Updated 7 months ago
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆76Updated 11 months ago
- Flexible and powerful multi-agent AI framework☆393Updated 2 weeks ago
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆348Updated 4 months ago
- II-Researcher: a new open-source framework designed to aid building search / research agents☆477Updated 3 months ago
- Official code of the ACL 2025 paper "SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation"☆128Updated 3 months ago
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆72Updated last week
- GraphRAG database - hybrid graph / vector db☆134Updated last year
- [NeurIPS 2025] Atom of Thoughts for Markov LLM Test-Time Scaling☆596Updated 5 months ago
- Super basic implementation (gist-like) of RLMs with REPL environments.☆248Updated last month
- ☆567Updated 6 months ago
- A user interface for DSPy☆195Updated last month
- ☆23Updated last year
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 9 months ago
- ☆271Updated 7 months ago
- ☆88Updated this week
- 🧬 The Huxley-Gödel Machine☆291Updated this week
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle☆299Updated 2 weeks ago
- ☆182Updated 9 months ago
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆344Updated last year
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆165Updated 2 months ago
- Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning☆436Updated last month
- ☆83Updated last week
- Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement☆141Updated 2 months ago