Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery
cs.AI
Submitted: 2026-11-09
Updated: 2026-11-13
Terminology
Sources
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
- EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
- AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era
- Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
- End-to-end autonomous scientific discovery on a real optical platform
- ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
- Kosmos: An AI Scientist for Autonomous Discovery
- Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark
- Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search
- Towards Execution-Grounded Automated AI Research
- ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
- FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
- IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
- AI Research Agents Narrow Scientific Exploration
- Cognitive Architectures for Language Agents
- Cognitive Foundations for Reasoning and Their Manifestation in LLMs
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