keskival / recursive-self-improvement-suiteLinks
A suite of open-ended, non-imitative tasks involving generalizable skills for large language model chatbots and agents to enable bootstrapped recursive self-improvement and an unambiguous AGI.
☆41Updated 10 months ago
Alternatives and similar repositories for recursive-self-improvement-suite
Users that are interested in recursive-self-improvement-suite are comparing it to the libraries listed below
Sorting:
- Automated Capability Discovery via Foundation Model Self-Exploration☆65Updated 10 months ago
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation☆49Updated last year
- A virtual environment for developing and evaluating automated scientific discovery agents.☆193Updated 9 months ago
- Evaluation of neuro-symbolic engines☆40Updated last year
- AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each…☆74Updated 3 weeks ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆189Updated 9 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆152Updated 10 months ago
- ☆34Updated 7 months ago
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆76Updated last year
- Fun project to run your own LLM chat bot using llama.cpp☆11Updated 2 years ago
- Mixing Language Models with Self-Verification and Meta-Verification☆110Updated last year
- Exploration using DSPy to optimize modules to maximize performance on the OpenToM dataset☆23Updated last year
- This repository contains popular code generation frameworks such as MapCoder, CodeSIM.☆67Updated 5 months ago
- LMQL implementation of tree of thoughts☆34Updated last year
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆133Updated last year
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆26Updated this week
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆34Updated 7 months ago
- Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement☆143Updated 2 months ago
- A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code you …☆81Updated 11 months ago
- Analysis code for Neurips 2025 paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆55Updated 4 months ago
- ☆63Updated 5 months ago
- ☆86Updated 2 years ago
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆85Updated 2 weeks ago
- ☆77Updated 2 months ago
- A benchmark that challenges language models to code solutions for scientific problems☆158Updated last week
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆84Updated 8 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆112Updated 4 months ago
- Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"☆62Updated 8 months ago
- LLM reads a paper and produce a working prototype☆60Updated 8 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆234Updated 4 months ago