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.
☆36Updated 4 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:
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents☆123Updated 11 months ago
- ☆50Updated last week
- Automated Capability Discovery via Foundation Model Self-Exploration☆50Updated 3 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…☆72Updated 5 months ago
- Collection of LLM completions for reasoning-gym task datasets☆23Updated last week
- Mixing Language Models with Self-Verification and Meta-Verification☆104Updated 5 months ago
- A benchmark that challenges language models to code solutions for scientific problems☆123Updated this week
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆68Updated 6 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆173Updated 2 months ago
- ☆82Updated last year
- Repository for the paper Stream of Search: Learning to Search in Language☆147Updated 4 months ago
- Functional Benchmarks and the Reasoning Gap☆86Updated 8 months ago
- accompanying material for sleep-time compute paper☆90Updated last month
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 4 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆89Updated last week
- Evaluation of neuro-symbolic engines☆35Updated 10 months ago
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆56Updated 5 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated last month
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆32Updated last month
- ☆40Updated 10 months ago
- ☆89Updated this week
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation☆42Updated last year
- Official code for the paper "ADaPT: As-Needed Decomposition and Planning with Language Models"☆80Updated last year
- A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive arguments☆81Updated 8 months ago
- Code for the paper: CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models☆21Updated 2 months ago
- This repository contains popular code generation frameworks such as MapCoder, CodeSIM.☆51Updated last month
- LMQL implementation of tree of thoughts☆34Updated last year
- Fun project to run your own LLM chat bot using llama.cpp☆11Updated last year
- 🤝 The code for "Can Large Language Model Agents Simulate Human Trust Behaviors?"☆81Updated 2 months ago
- A set of utilities for running few-shot prompting experiments on large-language models☆121Updated last year