CodeFest_AI_promt

CodeFestAIpromt: обзор исследований Логический вывод, метакогниция и мультиагентные системы на базе LLM

Содержание

1. Introspection of Thought Helps AI Agents

2. Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines

3. STAR-PólyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision

4. Tree of Thoughts: Deliberate Problem Solving with Large Language Models

5. MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs

6. Could you be wrong: Debiasing LLMs using a metacognitive prompt for improving human decision making

7. Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models

8. Accelerating Scientific Research with Gemini: Case Studies and Common Techniques

9. The Metacognitive Monitoring Battery: A Cross-Domain Benchmark for LLM Self-Monitoring

10. MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation