Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries

arXiv:2606.10402 · cs.CL, cs.AI · Submitted 2026-06-09 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-06-09

Updated: 2026-08-26

Code: https://github.com/vinid/einstein-arena

Terminology

• Verifier — 33× in this paper · explained in 2 episodes
• alpha — 11× in this paper · explained in 1 episode
• AI Agents — 8× in this paper · explained in 2 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Computational Biology — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• Kosmos: An AI Scientist for Autonomous Discovery
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
• AgentRxiv: Towards Collaborative Autonomous Research
• Multi-Agent Collaboration Mechanisms: A Survey of LLMs
• Astra: A Multi-Agent System for GPU Kernel Performance Optimization
• From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science
• The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
• AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
• Structured Scaling of AI Discovery Across Diverse Scientific Domains
• AFlow: Automating Agentic Workflow Generation
• SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
• Language Agents as Optimizable Graphs

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering