SciMARS: Multi-Agent Recursive Self-Improvement for Closed-Loop Scientific Discovery
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/WeiminWu2000/SciMARS
Terminology
Sources
- Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science
- Cell-JEPA: Latent Representation Learning for Single-Cell Transcriptomics
- ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization
- Recursive Self-Improvement through Multi-Agent Self-Supervision
- DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries
- POLO: Preference-Guided Multi-Turn Reinforcement Learning for Lead Optimization
- DiMOS: Doob-Guided Inference-Time Multi-Objective Search for Scientific Design
- Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models
- Harness 2: Recursive Agent Harnessing for an Open World
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents