OpenDCAI / SciAgentLinks
SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning
☆91Updated 2 months ago
Alternatives and similar repositories for SciAgent
Users that are interested in SciAgent are comparing it to the libraries listed below
Sorting:
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning☆92Updated last month
- ☆95Updated last week
- Analysis code for Neurips 2025 paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆56Updated 5 months ago
- ☆19Updated 10 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆102Updated 4 months ago
- ☆29Updated 2 months ago
- Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"☆125Updated last week
- This repository contains popular code generation frameworks such as MapCoder, CodeSIM.☆69Updated 7 months ago
- ☆61Updated 7 months ago
- The original Shared Recurrent Memory Transformer implementation☆33Updated 6 months ago
- [ACL 2025] Agentic Knowledgeable Self-awareness☆91Updated 7 months ago
- ☆67Updated 10 months ago
- ☆42Updated 8 months ago
- MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning☆111Updated 2 months ago
- ☆20Updated 6 months ago
- Graph-Aware Attention for Adaptive Dynamics in Transformers☆68Updated last year
- ☆15Updated 9 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆141Updated last year
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆92Updated last year
- Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization☆38Updated 2 months ago
- Codebase from our first release.☆41Updated 3 weeks ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆88Updated 10 months ago
- AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents☆36Updated 3 months ago
- Demystifying Reinforcement Learning in Agentic Reasoning☆159Updated 3 months ago
- Official Repository of Native Parallel Reasoner☆100Updated last week
- ☆159Updated last month
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆76Updated last year
- Marketplace ML experiment - training without backprop☆27Updated 4 months ago
- Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)☆128Updated 11 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆168Updated 5 months ago