A Bifurcation-Theoretic Framework for the Controllability of Emergent Intelligent Systems
cs.AI, cs.SY, eess.SY, nlin.AO
Submitted: 2026-11-09
Updated: 2026-11-09
Comments: 21 pages, 1 figure, 5 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- The Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to Engineering
- Concrete Problems in AI Safety
- Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
- Thermal fluctuations set fundamental limits on ion channel function
- Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
- From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
- Continuous tuning of quantum critical behavior in hybrid Josephson junction arrays
- Toward a Physics of Deep Learning and Brains
- Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation
- AI Control: Improving Safety Despite Intentional Subversion
- Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems
- Rice's Theorem under Self-Modification: Elevation Operators and a Normal Form
- Evidence of Phase Transitions in Small Transformer-Based Language Models
- Engineering Emergence
- The Universal Weight Subspace Hypothesis
- Measuring Determinism in Large Language Models for Software Code Review
- SWE-PRBench: Benchmarking AI Code Review Quality Against Pull Request Feedback
- Debate Helps Weak-to-Strong Generalization
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